DESTINY
PLANNING AND
FORECASTING SYSTEM
Module 1: Single-Country Programs
User's
Manual
FORTRAN
Version 1.0
Reformatted
Joseph
George Caldwell, PhD
Tel.
(001)864)439-2772, e-mail jcaldwell9@yahoo.com
Internet website http://www.foundationwebsite.org
Copyright
© 1982, 1995, 2005 Joseph George Caldwell. All rights reserved.
Table of
Contents
II. How to Use the PARAM Program to Create
Parameter Files
B. File Names; File Structure (Input Option)
Parameters;
C. Demographic Parameters and Data
D. Service-System (Program-Related) Parameters
and Data
III. How to Use the CHECK Program to Print a
Parameter File
IV. How to Use the PROJ Program to Make
Projections
V. How to Use the CHECK Program to Adjust
Service-System Parameters
VI. Example 1: National Population Projection,
Single-Race Model
A. Projection Objectives; Data Sources
VII. Example 2: National Population Projection,
Two-Race Model
A. Projection Objectives; Data Sources
VIII. Example 3: State Population Projection,
Single-Race Model
A. Projection Objectives; Data Sources
IX. Example 4: State Population Projection,
Three-Race, 14-Region Model
A. Projection Objectives; Data Sources
X. Example 5: Projection of the Hispanic
Population
A. Projection Objectives; Data Sources
XI. Example 6: Rehabilitation Services,
Projection of the Work-Disabled
A. Projection Objectives; Model Structural
Parameters
XII.
Example 7: Education, Projection of School Enrollment
A. Projection Objectives; Model Structural
Parameters
XIII. Example 8: Criminal Justice, Projection of
Prison Admissions and Operating Cost
A. Projection Objectives; Model Structural
Parameters
XIV. Example 9: Health Care, Projection of the
Need for Short-term and Long-term Beds
A. Projection Objectives; Model Structural
Parameters
A. Projection Objectives; Model Structural
Parameters
Appendix
A. Data Sources, Model Parameterization
and Model Calibration
Appendix
D. Computer Program Output Listings
The DESTINY computer
program package is designed to project populations and estimate quantities
related to population. The estimated
quantities may be occurrences of events, such as school enrollments or prison
admissions or occurrences of diseases or accidents; or they may be special
populations of interest, such as the population of students, of nursing home
beds, or persons having certain disabling conditions.
An overall description of the DESTINY system and its
uses is presented in a separate manual, DESTINY Planning and Forecasting
System: Description of Capabilities (Reference 1). This User's Manual provides a detailed
description of procedures for using the system.
A primary objective of the DESTINY system is to enable
the user to make population projections and population-related estimates using
readily available demographic data about the general population and target or
service populations of interest. In
addition to describing how to use the DESTINY computer programs, much of the
information presented in this manual is intended to identify sources for the
needed program input data, or show how to obtain the needed data from related
data, in cases where the exact data desired are not available.
The DESTINY computer program package consists of three
computer programs, called PARAM, CHECK, and PROJ. Three separate programs are used instead of
one in order to minimize the internal memory, direct-access (core) storage
requirements of the package. The PARAM
program sets up a parameter file, which contains demographic information about
the population of interest, and programmatic information about the target
populations and service system under study.
The CHECK program is used to print out the contents of the parameter
file, so that a "hard copy" printout of all parameters can be
retained as documentation for the projection runs. This program is also used to make minor
adjustments to some of the service-system parameters. The PROJ program operates on the data files
created by PARAM and CHECK, and generates the desired population projections
and forecasts of program-related quantities of interest, such as service
requirements, resource utilization, and cost.
Figure 1, Major Components of the DESTINY System,
illustrates the relationship of the three programs, PARAM, CHECK, and
PROJ. In Figure 1, the data files
created by PARAM, CHECK and PROJ are called AZ803.DAT and AZ803CS.DAT. (A recommended procedure for naming files is
discussed later. With this procedure,
each letter of the file name indicates something about the nature of the
file. In the name AZ803CS.DAT, for
example, AZ stands for
Figure 1. Major
Components and Functions of the DESTINY System
1. Program
PARAM: Creation of Parameter File
┌────────────────┐ ┌──────────┐ ┌────────────────────┐
│ "Old" Parameter│ │ Program │ │
"New" Parameter │
│ File AZ803C.DAT├─┤ PARAM ├─┤ File AZ803CS.DAT │
│ (if
any) │
└──────────┘ └────────────────────┘
└────────────────┘
2. Program
CHECK: Printout of Parameter File
┌───────────────┐ ┌─────────┐ ┌──────────────────────┐
│ Parameter File│ │ Program │ │ Printout of all
│
│ AZ803CS.DAT├─┤ CHECK ├─┤ parameters in │
└───────────────┘ └─────────┘ │ AZ803CS.DAT;
Total │
│ Fertility Rate check │
└──────────────────────┘
3. Program
PROJ: Computation of Projections
┌────────────────┐
│ Parameter File │
│
AZ803CS.DAT ├───┐ ┌─────────┐ ┌────────────────────┐
└────────────────┘ └──┤ Program │ │ Printed
Output │
┌───────────────────┐┌──┤ PROJ ├─┤ (Projections, │
│ Run-Time Commands ├┘ └─────────┘ │ crosstabulations) │
│ (No. of years to
│ └────────────────────┘
│ project, cross-
│
│ tabulations to
│
│ print)
│
└───────────────────┘
4. Program
CHECK: Adjustment of Service-System Parameters (Optional)
┌─────────────────┐ ┌─────────┐ ┌────────────────────────┐
│ "Old" Parameter │ │ Program │ │ "New" Parameter File
│
│ File AZ803CS.DAT├─┤ CHECK ├─┤ AZ803CS2.DAT (has same │
└─────────────────┘ └─────────┘ │ structure as │
│ AZ803CS.DAT, but
│
│ adjusted service-system│
│
data) │
└────────────────────────┘
The PARAM program is used to set up a parameter file,
or to update a parameter file. The first
time that PARAM is used, there is no "old" parameter file -- the
program is used the first time to set up only a "new" parameter file,
AZ803C.DAT, which is stored on the computer's disk. After this first parameter data file is
created, it is then referred to as an "old" parameter file, and it
may be modified (for example, by changing an infant mortality rate or a
migration rate, or by adding service-system data.) These changes are incorporated into a
"new" parameter file, AZ803CS.DAT, which is also stored on disk. The "old" parameter file,
AZ803C.DAT, is unchanged -- it remains on the disk exactly the same as before.
After the parameter file (AZ803C.DAT the first time,
AZ803CS.DAT in later runs) has been created, the program CHECK should be
run. This program prints out all of the
parameter values that are contained in AZ803CS.DAT. This printout is useful in two ways -- first,
it facilitates a detailed review of all of the parameter values, which review
should be conducted to be sure that all of the parameter values have been entered
correctly; and second, it represents a permanent record of the parameter values
stored in AZ803CS.DAT, which record would be retained as documentation for the
projection runs produced by the PROJ program, using the parameter file
AZ803CS.DAT.
In addition to producing a hard copy printout of the
contents of the parameter file, CHECK also prints out information concerning
the Total Fertility Rate specified in the parameter file. It estimates the Total Fertility Rate from
the base-year crude birth rate and age/sex population distribution, so that the
user may compare it to the value specified for the first five-year projection
period. It also estimates the annual net
migration for the past ten years.
If the user wishes to modify any of the data values in
the data file, he may rerun the PARAM program to change them. If the user wishes only to make scaling
adjustments to the values of service-system parameters (without changing the
numbers of parameters in the file), this may be done more easily by rerunning
the CHECK program (than by rerunning PARAM).
This option is used after the user has made his first run of the
projection program, PROJ, and may wish to modify some of the service-system
parameters in order to "calibrate" the model to match certain known
base-year quantities (such as total budgets.)
The PARAM program asks the user to enter the name of
the old and new parameter files, and the values of the various parameters
required to make projections. The CHECK
program asks for the name of the parameter file, and, if it is being used to
modify service-system parameters, for the values of the adjustment factors.
After the programs PARAM and CHECK have been run, the
program PROJ is executed to construct the desired projections. The PROJ program asks the user for very
little data -- the number of five-year periods to project, the kinds of crosstabulations that are desired, and whether single-year
projections (between successive five-year intervals) are desired (and if so,
for which years). The PROJ program reads
the data file created by PARAM (and perhaps modified by CHECK).
The preceding paragraphs have described the overall
way in which the DESTINY package works.
The following chapters describe in detail how to use each of the three
component programs, PARAM, CHECK, and PROJ.
The PARAM program sets up a parameter data file
containing the following categories of information:
o File Names; File Structure (Input Option) Parameters
o Demographic Parameters (one complete set of data is
required for each race)
o Total fertility
Rate
o Fertility Age
Distribution
o Infant
Mortality Rates or Expectation of Life at Birth
o Base-Year
Population, Other Base-Year Data, and Data for the Ten-Year Period Prior to the
Base Year
o Regional
Populations (if the model includes more than one region; for base year and ten
years previous)
o External
Migration Parameters
o Internal
Migration Parameters (if the model includes more than one region)
o Service-System
(Program-Related) Parameters (Optional)
o Program Data
Parameters
o Target
Population Incidences or Prevalences
o Service
Population Service Ratios
o Service Unit
Data
o Resource Unit
Data
o Cost Data
o Names (Required)
o Race/Ethnic
Group Names
o Region Names
o Target
Population Names
o Service
Population Names
o Service Names
o Resource
Names
o Cost Category
Names
The sections that follow define each of the variables which
characterize the above information categories, and describe in detail how to
input them to the computer terminal.
Appendix A indicates likely sources for the data required by PARAM. Appendix B contains data entry forms that can
be used to record the data in an organized format, prior to entry into the
computer. Appendix D includes some
technical information concerning the analytical methodology used by the DESTINY
package.
The PARAM program is executed by typing PARAM at the
MS-DOS prompt. The first information
required by the program is an Authorization Code -- an eight-digit code which
must be input by the user before the program will work. The Authorization Code is recorded on the
DESTINY Lease Agreement Form. The PARAM
program prints the following line on the video monitor:
ENTER
AUTHORIZATION CODE: .
If the Authorization Code were ABC123, for example,
the user would type ABC123 on the keyboard (using capital letters), and then
depress the ENTER key:
ABC123
(ENTER) .
(Note: the symbol (ENTER) indicates that the
"ENTER" key on the keyboard is to be depressed.) No spaces should be typed before the code, or
between any of its characters.
Next, the PARAM program states:
ENTER 0 TO
MODIFY EXISTING FILE, 1 TO CREATE FILE FROM SCRATCH:
The first time the program is used, there is no
existing file which can be modified, and the user must enter all of the data
from scratch, i.e., a "1" should be entered:
1 (ENTER) .
For subsequent uses, the user will generally update an
existing parameter file, and enter a "0". For example, the user will probably create a
base-year population file containing only demographic information, and update
this file on numerous occasions to create files that contain data on certain
target populations. In such a case, all
of the demographic data in the "demographic" file are simply copied
into the new file without change, and the new target-population or
service-system data are added to the file.
If the user inputs a "0" (to update an
existing parameter file), the program reads through the file section by
section, and shows the user what parameter values are stored in the existing
file. The program then asks for each
section whether to use the existing values, or whether different values are
desired. If the user chooses to accept
the existing values in a section, he types a "0" (or nothing), and depresses
the ENTER key. If the user wishes to input
different values in a section, he enters a "1" (i.e., types a
"1" and depresses the ENTER key).
Since the manner in which updated data are entered in each section is
exactly the same as the manner in which new data are entered the first time
PARAM is run, we shall discuss in this section only the latter case, in which a
new parameter file is being constructed from scratch. We assume that the user enters a
"1" in response to the question:
ENTER 0 TO
MODIFY EXISTING PARAMETER FILE, 1 TO CREATE
FILE FROM SCRATCH: .
The next request printed by the program is:
ENTER NAME
OF NEW PARAMETER FILE (12X): .
The notation (12X) in parentheses is a format
descriptor. It indicates that up to 12
characters may be used in the file name.
The user may input any valid MS-DOS file name (eight-digit alphanumeric
name beginning with a letter, followed by a period, followed by three
additional characters), such as US801.DAT or AZ803C.DAT. The use of easily-remembered mnemonics which
suggest the contents of the file is recommended. It is suggested that the first two characters
be used to denote the geographic region (e.g., US or AZ); the next two
characters the last two digits of the base year (typically a census year, such
as 80 or 90); the next character the number of races (or a letter denoting one
of two races); and the next the type of region.
The seventh character may describe the nature of a target population to
be described by the file, e.g., S for social services. The eighth character may be used for any
purpose, such as a file version number (e.g., 1, 2, a, b). The final three characters (the "file
extension," following the period), may be any characters, such as DAT (for
"data"), or DBF (for "data base file"). (It is best to use the same three-character
extension for all data files, to facilitate copying of those files to a floppy
disk by means of a command such as COPY
*.DAT A:/V .)
For example, the mnemonic AZ803CS.DAT refers to a
parameter file containing data for the state of Arizona (AZ); base year 1980,
3 races; countries; and social services to the elderly.
To input the file name, simply type it on the
keyboard, using capital letters, and depress the ENTER key. For example,
AZ803C.DAT (ENTER) .
On later runs, the user will usually be updating an
existing file, and will enter a "0" in response to the request
concerning whether an existing parameter file is to be modified, or a new file
created from scratch. The user would be
instructed:
ENTER NAME OF OLD PARAMETER FILE: ,
to which request he might enter:
AZ803C.DAT (ENTER) .
The next command would then be:
ENTER NAME OF NEW PARAMETER FILE: ,
to which request he might respond with the entry:
AZ803CS.DAT (ENTER) .
The next information requested by the program is a
"header" for the parameter file -- a descriptive title for the
parameter file, consisting of up to 80 characters. The program prints out:
ENTER FILE
HEADER. INCLUDE NAME OF GENERAL
POPULATION; NATURE OF
RACIAL/ETHNIC AND REGIONAL DISAGGREGATION: NATURE OF TARGET POPULATIONS AND
SERVICE SYSTEM. FORMAT 80X.: .
The header would include the following information:
o Name of the
general population being projected
o Nature of the
racial/ethnic and regional disaggregation
o Nature of the
target populations and service system.
For example, if the parameter file will refer to the
resident population of the state of Arizona, will be disaggregated by three
races (white, Indian, and other), will include 14 countries, and will include
data concerning social services to the elderly population, then the user might
enter the following header:
After the header, the program prompts the user to
enter the base year to which the population applies. This number is typically a decennial census
year (for which much demographic data are available), such as 1980 or 1990. This number should be four digits long, e.g.,
1980. The program requests:
INPUT BASE
YEAR: ,
to which the user might respond, for example,
1980
(ENTER) .
After the file name(s), header, and base year have
been entered, the next input parameters required by the PARAM program allow the
user to specify which of a number of options he wishes to use, in constructing
the parameter data file. These options
indicate both the types of data to be specified by the user, and the level of
detail of the data. The seven parameters
(denoted by P1, P2,..., P7 in this document) are as follows:
P1: Number of Races (1-3)
P2: Number of Regions (1-14)
P3: Vital Statistics Parameter Option (1 or 2)
P4: Life Table Option (1 or 2)
P5: External Migration Parameter Option (0, 1, or
2)
P6: Internal Migration Parameter Option (0 or 1)
P7: Service System Option (0 or 1)
The significance of each parameter option is as
follows.
P1: Number of Races (1-3)
The program requests:
ENTER NO OF RACIAL/ETHNIC GROUPS (1-3): .
The user specifies the number of races (from 1 to 3)
for which he plans to enter a complete set of demographic data (fertility
rates, migration rates, base year populations, and so forth). The user should enter the number of
racial/ethnic groups for which he wants breakdowns of the data in the
projections, or for which he wishes to specify different demographic or
programmatic parameters. If projections
are to be made for a state in which there are three major racial/ethnic groups,
and projections are desired by race, then a "3" should be entered (by
striking a "3" on the keyboard, followed by "ENTER"). Alternatively, if the user is not interested
in projections broken down by race, he could specify a "1" for the number
of races, in which case all subsequent demographic parameters entered to the
program would refer to the entire state (i.e., the total population of all
races combined).
It is emphasized that all of the demographic data
items (described later) must be entered for each race specified.
P2: Number of Regions (1-14)
The program requests:
INPUT NO OF REGIONS (1-14): .
The user may specify up to fourteen geographic
regions. If no regions are specified,
the user enters a "1" (or a "0" or nothing). By specifying more than one region, the user
may later request in a PROJ run that the projections be broken down by
region. If two or more regions are
specified, then the user must (at a later step) specify the population of each
region, for each racial/ethnic group.
P3: Vital Statistics Parameter Option (1 or 2)
The program requests:
ENTER VITAL
STATISTICS PARAMETER OPTION (1 OR 2): .
The Vital Statistics Parameter Option allows the user
to specify that the following parameters:
o Total Fertility
Rate
o Fertility Age
Distribution
o Infant
Mortality Rate
o Expectation
of Life at Birth
are either the same for all future time (i.e., for all
ten five-year projection periods), or are different for each of the ten
five-year projection periods. The user
enters a "1" for the former option (parameter values the same for all
the future) and a "2" for the
latter option (different parameter values for each five-year period).
P4: Life Table Option (1 or 2)
The program requests:
ENTER LIFE
TABLE OPTION (1 OR 2): .
The DESTINY package uses the Coale-Demeny
"West" model life tables to determine the probability that an
individual survives each five-year period of his life. These tables specify the survival
probabilities either as a function of the infant mortality rate or as a
function of the expectation of life at birth.
The user indicates which table to use by specifying a value for either
one of these two parameters. The Life
Table Option parameter is set equal to "1" in order to use infant mortalities
to determine the appropriate life table, and "2" to use expectations
of life as the determining parameter. It
is recommended that Option 1 be used for countries having high mortality rates
(e.g., most developing countries) and Option 2 for countries having relatively
low mortality rates (e.g., the
P5: External Migration Parameter Option (0, 1, or 2)
"External" migration refers to migration
between the area under study and outside areas, e.g., migration into and out of
a state or into and out of a country.
"Internal" migration (the subject of Input Parameter P6)
refers to population movements among the various subregions
of the area under study, such as population movements among states, provinces,
or regions in the case of a country, or movements among countries or other substate regions or districts in the case of a state.
The program requests:
ENTER
EXTERNAL MIGRATION OPTION (0-2): .
The five options that are available for specifying
external migration are as follows:
o Option 0. No net external migration, either into or out
of the geographic area under study, is allowed, i.e., there is no net
immigration ("in-migration") or emigration
("out-migration").
o Option 1. The same migration rate is used for
all ten five-year projection periods (of
the next fifty years), or the same migration amount, or number,
is used for all ten five-year projection periods. (Note: Since all demographic parameters are
specified separately for each race, a different rate or number may be specified
for each race.)
o Option 2. A separate migration rate or migration number
is specified for each of the ten five-year projection periods. (Note: These parameters may vary by race.)
A migration rate is the average proportion of
the population moving out of the area each year; the rate is expressed in the
net number of persons entering or leaving an area per 1,000 persons per
year. A migration number is the
average number of persons moving into or out of an area each year. The migration rate or the migration number
are used to specify net immigration (in-migration). The user may specify either a migration rate
or number, but a (negative) migration rate should be specified in cases
of net population loss and a (positive) migration number should be used
in cases of net population gain (although there is no requirement for this
convention). Additional discussion of
migration rates and numbers will be presented later.
Option 0 would be used in a run to determine the
"rate of natural increase" -- i.e., the growth rate of a population
due to births and deaths, ignoring changes due to migration.
P6: Internal Migration Parameter Option (0 or 1)
"Internal migration" refers to the
redistribution of the population among the region to area under study, due to movements
of the residents of one region to another region, to settlement of the external
migrants (from outside the area), and to emigration of the residents of regions
to places outside the area under study.
The program requests:
ENTER
INTERNAL MIGRATION OPTION (1 or 2): .
Two options are available for specifying internal
migration:
o Option 0. No internal migration.
o Option 1. For each region, the user must specify an
annual growth rate or amount, net of births, deaths, and a proportional
allocation of external migration to the regions. (Note: Different parameter values may be
specified for each race.)
Since internal migration is an inter-regional
phenomenon, the Internal Migration Option operates only if there is more than
one region. If there are no regions
specified, Option 0 is used.
The growth rate is the average rate of population
change in a region per 1,000 population per year.
P7: Service System Option (0 or 1)
The program requests:
ENTER
SERVICE SYSTEM OPTION (0 0R 1): .
The DESTINY package may be used solely to make
projections of the general population, or to make projections of target
populations (subpopulations of interest), program services, resources, and
costs. To make only general population
projections, enter a "0"; to use the full capability of the program
to forecast the program-related items as well, enter a "1".
After the demographic parameter options have been
specified, the program asks for the names of the races (or ethnic groups) and
regions (if any). The request is:
ENTER NAME
FOR RACE NO i (8X): .
where i ranges from 1 to the
number of races specified (i.e., 2 or 3).
The user may specify any eight-character name for the race, such as
WHITE, BLACK, OTHER, HISPANIC, or AMERIND.
The program next requests the user to input the names
of the regions, if two or more regions are included in the model:
ENTER NAME
FOR REGION NO i (8X): .
For a country, the regions might be states, provinces
or major geographic regions. For a state
or province, the regions might be districts or counties. For a local area such as a city, the regions
might be the metropolitan and nonmetropolitan
areas. If names such as "REGION
1" are used, a space may separate the word and the number, as long as the
total number of characters, including blanks, is less than or equal to
eight. Hence, "REGION 10" is
not allowed -- if it were entered, the eleventh character (the "0")
would be dropped.
If PARAM is being used to update an existing parameter
file, the user will be asked whether he wishes to keep all of the Demographic
Option Parameters the same as in the old file, or whether he wishes to change
(all of) them. If he keeps them the
same, PARAM simply reads them from the old file and writes them into the new
file. If he wishes to change them, he
must input the new values through the keyboard.
This process (i.e., accept the old file values or enter new values) is
used for all of the remaining parameter categories that follow.
A complete set of demographic parameters must be
specified for each race represented in the parameter data set. When PARAM is used to construct a
"new" parameter file from scratch (such as is the case the first time
the DESTINY package is used), the program input section makes one complete
input "cycle" for each race, and requests the user to enter values
for all of the required demographic parameters.
If program is used in the update mode (i.e., a new parameter file is
being constructed by modifying an existing file), then the program input
section cycles through each of the races in the old parameter file, each time
asking whether the user wishes to save (i.e., write to the new file) or update
the data for that race. Then, after all
of the races of the old parameter file have been reviewed (and either saved or
updated), the program recycles to permit entry of additional races. This process stops when demographic data have
been modified or input anew for as many races as were specified in the Input
Option Parameter section. For each
cycle, the following information is requested:
o Total Fertility Rate(s)
o Fertility Age Distribution(s)
o Infant Mortality Rate(s) or Expectation(s) of
Life at Birth
o Base-Year Population
o External Migration Parameter(s)
o Regional Populations (if regions are included
in the model; for the base year and ten years previous)
o Internal Migration Parameter(s) (entered if
the model contains more than one region)
The paragraphs that follow describe the data entry
procedure for each of the preceding information categories. The data entry is illustrated with sample
values, without describing the source of those sample values. Later chapters will describe in detail the
procedures for obtaining proper values for the model parameters.
Total Fertility Rate(s)
The total fertility rate is the average total number
of live births per female in her lifetime.
For the
If Input Option Parameter P3 is a "1", then
only one rate is required (per race), and this rate applies to all future time
periods. In this case, the program
requests:
ENTER 1 TOTAL FERTILITY RATE(S) (10X.XXX): ,
and the user must enter one decimal number. If Option P3 is specified as a "2",
then the program requests:
ENTER 10
TOTAL FERTILITY RATE(S) (10X.XXX): ,
and the user must input ten decimal numbers. The rules for entry of these numbers will now
be described.
The format X.XXX in the data entry request indicates
that the Total Fertility Rate must be entered to the computer as a decimal
number (e.g., 1.799), with no more than one digit before the decimal and no
more than three digits after the decimal.
If a rate of 2.0 were to be specified, it must be entered as
"2.", or "2.0", or "2.00", or "2.000", with
the decimal point, not as "2" with no decimal point. Each time PARAM requests one or more
numerical values to be entered, it indicates the format of the number by means
of an expression such as "X", "7X", "16XX.XX", or
"8XXXXXXXXX.", where a digit is to be substituted for each
"X" (or, in the case of names, any alphanumeric character is to be
substituted for each "X".) The prefix number (7, 16, and 8 in the
preceding examples) indicate how many values are to be specified (if available)
before depressing the "ENTER" key.
The position of the decimal point does not matter, as long as it is
present somewhere in the number. For
example, if the user wanted to enter the following ten Total Fertility Rates
(one for each of the ten five-year projection periods) according to the format
10X.XXX, then the following entry would be acceptable:
1.875,1.85,1.8,1.75,1.75,1.75,1.75,1.75,1.75,1.75 (ENTER).
Note that it is not necessary to have three digits
following each decimal point, as suggested by the format. The numbers may not, however, have more than
one digit before the decimal, nor more than three digits after the
decimal. If the user violates these rules,
the extra digits will be lost, and the wrong values entered into the parameter
file.
The user has a choice of either following the
specified format exactly, or separating each number by commas. For example, if the format were 3X.XXX, and
the user wished to enter the numbers .75, 1.2, and .9, then either of the
following entries would be acceptable:
0.75±1.2±±.9 (ENTER) ,
where ± represents a blank
(obtained by depressing the space bar), or
.75,1.2,.9
(ENTER) .
If commas are not used, each number must utilize
exactly the same number of positions (including digits, decimal point, minus
sign, or blanks) as specified in the format descriptor. In the preceding example, each number of the
entry must take up exactly five positions if no commas are used. In general, it is simpler to use commas to
separate all decimal numbers, but to use no commas when entering small integer
numbers. For example, if the user wished
to enter the numbers 1,0,1,1,0,1,0,0,1 according to the format 9X, it is
simpler to enter
101101001
(ENTER) ,
rather than
1,0,1,1,0,1,0,0,1 (ENTER) .
Fertility Age Distribution(s)
The Fertility Age Distribution indicates what
proportion of a woman's children are born in each five-year period of
life. For example, in the
Birth
Rate
(per
1000 women in
Age of
Mother specified age group) Proportion
Under
20 53.6 .15
20-24 112.3 .31
25-29 112.0 .31
30-34 59.1 .17
35-39 18.9 .05
40+ 4.1 .01
360.0 1.00
Note that the Total Fertility Rate (1.799) is equal to
the sum of the birth rates (360.0) divided by 1000 (the number of women) and
multiplied by 5 (the number of years), i.e., 1.799 = 360.0 x 5.0 / 1000. (The arithmetic would actually produce 1.800,
not 1.799; the value 1.799 published in vital statistics documents for 1978 is
the result of more precise computations, which carried more decimal places in
the birth rates.) Possible sources of
demographic data such as the fertility age distribution are identified in
Appendix A.
If Input Option Parameter P3 is a "1," the
user need input but a single Fertility Age Distribution, consisting of six
decimal numbers that total to 1.0. The
program requests:
ENTER
FERTILITY AGE DISTRIBUTION (6 ENTRIES, FORMAT 6X.XXX) FOR PERIOD NO 1: .
To enter the Fertility Age Distribution illustrated in
the preceding example, the user would enter:
.15,.31,.31,.17,.05,.01 (ENTER) .
If Input Option Parameter P3 is a "2,, the user
must enter ten such six-number distributions, one for each of the ten five-year
projection periods.
Infant Mortality Rate(s)
The Infant Mortality Rate is the number of infant
deaths per 1000 live births (where an "infant death" is the death of
an infant under one year of age, excluding fetal deaths.) For the
The PARAM program will accept Infant Mortality Rates
whose values lie between 11.25 and 530.76.
If Input Option Parameter P3 is a "1," the
program requests:
ENTER 1
INFANT MORTALITY RATE(S) (10XX.XX): ,
to which the user might respond, for example,
13.8
(ENTER) .
If Input Option Parameter P3 is a "2," ten
such numbers must be entered, one for each five-year period into the future.
Expectation of Life at Birth
The Expectation of Life at Birth is the average number
of years to be lived by a newborn, assuming that the mortality rates for each
age group remain constant in the future.
For persons born in the
PARAM will accept values of the expectation of life at
birth between 19.02 and 75.70.
If Input Option Parameter P3 is a "1," the
program requests:
ENTER 1
EXPECTATION(S) OF LIFE AT BIRTH (10XX.XX): ,
to which the user might respond
70.00
(ENTER) .
If Input Option Parameter P3 is a "2," then
ten such numbers must be entered.
Note that, depending on the value of the Life Table
Option Parameter P4, the user specifies either Infant Mortality Rates or
Expectations of Life at Birth, but not both.
Base-Year Population, Other Base-Year Data, and Data
for the Ten-Year Period Prior to the Base Year
Base-Year Population The program requests entry of
the base-year population by thirty-two age x sex categories -- sixteen
five-year intervals by two sexes. To
illustrate, the following table presents the
Age Male Female
0-4 8,360,135 7,984,272
5-9 8,537,903 8,159,231
10-14 9,315,055 8,925,864
15-19 10,751,544 10,410,123
20-24 10,660,063 10,652,494
25-29 9,703,259 9,814,413
30-34 8,675,505 8,882,452
35-39 6,860,236 7,102,772
40-44 5,707,550 5,960,689
45-49 5,387,511 5,700,872
50-54 5,620,474 6,088,510
55-59 5,481,152 6,132,902
60-64 4,669,307 5,416,404
65-69 3,902,083 4,878,761
70-74 2,853,116 3,943,626
75+ 3,547,402 6,419,145
Total 110,032,295 116,472,530
Grand Total 226,504,825
Source: 1980 Census of Population, Supplementary
Reports, PC80-S1-1, Age, Sex, Race, and Spanish Origin of the Population by
Regions, Divisions, and States: 1980, Table 1. "Population of the
United States by Age, Sex, Race, and Spanish Origin, 1980, US Department of
Commerce, Bureau of the Census (for sale by the Superintendent of Documents,
Washington, DC 20402), issued May, 1991.
This report presents resident population, i.e., excluding Armed Forces
overseas.
The program requests:
ENTER
BASE-YEAR POPULATION, BY AGE (16 ENTRIES, FORMAT 8XXXXXXXXX.) FOR SEX = i: ,
where i = MALE or
FEMALE. The format 8XXXXXXXXX. indicates
that these data are to be entered as decimal number of up to nine digits each
(plus a decimal), eight at a time. In
the preceding example, the data would be entered in four steps, as follows:
8360135.,8537903.,9315055.,10751044.,10660063.,9703259.,8675505.,6860236.
(ENTER)
5707550.,5387511.,5620474.,5481152.,4669307.,3902083.,2853116.,3547402.
(ENTER)
7984272.,8159231.,8925864.,10410123.,10652494.,9814413.,8882452.,7102772.
(ENTER)
5960689.,5700872.,6088510.,6132902.,5416404.,4878761.,3943626.,6419145.
(ENTER)
Each of the four sets of entered data should be typed
on a single line, not on two lines as shown here. Note that commas may be used as delimiters
between the data values, but they must not be used within each number.
Exactly eight population entries must be typed prior
to each depression of the ENTER key. If
fewer than eight entries are typed, the remaining entries (up to eight) will be
recorded as zeros. If more than eight
entries are typed, they will be lost.
Note that, just as is the case for all other
demographic parameters, a separate set of base-year population figures is
required for each race being considered.
In the preceding example, no racial structure would have been specified
for the model, and the population value for each age x sex category includes
persons of all races.
Other Base-Year Data The following additional
base-year data:
o crude birth rate
o crude death rate
o infant mortality rate
are entered.
The first two of these data elements are used, along with the base-year population,
to determine an estimate of the Total Fertility Rate for the base year. This estimate may be used if reliable data on
the Total Fertility Rate are not available from published sources. The last data item (infant mortality rate for
the base-year period is not presently used in the model computations; it is
entered for display purposes along with other demographic data.
The program makes the following three requests:
ENTER CRUDE BIRTH RATE (PER 1000) FOR BASE YEAR
(FORMAT
XXX.XX):
ENTER CRUDE DEATH RATE (PER 1000) FOR BASE YEAR
(FORMAT
XXX.XX):
ENTER INFANT MORTALITY RATE (PER 1000) FOR BASE YEAR
(FORMAT
XXX.XX):
to which the user might provide, for example, the
values 15.90, 8.70, and 13.80.
Data for the Ten-Year Period Prior to the Base Year In order to
estimate migration, the program uses the following data for the ten-year period
preceding the base year:
o Population ten years prior to the base year
o Average crude birth rate for the ten-year period
prior to the base year
o Average crude death rate for the ten-year period
prior to the base year.
In addition, for display/comparison purposes, the
following data element is requested:
o Average infant mortality rate for the ten-year period
prior to the base year.
The program makes the following requests:
ENTER POPULATION TEN YEARS PRIOR TO BASE YEAR (FORMAT
XXXXXXXXX.):
ENTER AVERAGE CRUDE BIRTH RATE (PER 1000) FOR PREVIOUS
TEN YEARS
(FORMAT XXX.XX):
ENTER AVERAGE CRUDE DEATH RATE (PER 1000) FOR PREVIOUS
TEN YEARS
(FORMAT XXX.XX):
ENTER AVERAGE INFANT MORTALITY RATE (PER 1000) FOR
PREVIOUS
TEN YEARS (FORMAT XXX.XX):
to which the user might provide, for example, the
values 203302301., 15.90, 8.70, and 13.80.
External Migration (Total Net Migration for All
Regions)
As mentioned earlier, the PARAM program allows five
options for entry of migration information.
The migration data describe the total migration for all regions. The manner in which the migration is
associated with the various regions of the model (if the model contains more
than one region) is described in the following section (on internal migration).
The data entry for the five external migration options
(0-2) are described below.
o Option 0. No net external migration; no data
entered.
o Option 1. The user specifies (for each race)
a single annual migration rate or a single annual migration number (amount),
which apply to all future five-year projection periods. (In the model, the total number of net
migrants (immigrants and emigrants) is allocated to each age x sex cohort
(category) in proportion to the size (population) of each cohort.)
o Option 2. The user specifies a separate
migration rate or migration number for each of the ten five-year projection
periods. (As with Option 1, the model
allocates the total number of net migrants (immigrants or emigrants) to each
age x sex cohort in proportion to its size.)
The migration rates and migration numbers are annual
values, and the rates are per 1,000 persons.
The migration rate is the average net number of immigrants (persons
moving into the area) per 1,000 persons per year. The migration number is the average net
number of immigrants per year. The term
"net" refers to the difference between immigrants and emigrants. Net migration may be positive or negative.
Net migration rates and numbers may be either positive
(net gain in population from immigration and emigration) or negative (net loss
in population from immigration and emigration).
For example, a migration rate of -1.0 represents a net emigration
of one person per 1,000 population per year from an area. Similarly, a migration number of -7,000
represents a net emigration of 7,000 persons from an area.
Migration rates and numbers are intended to represent
total net migration for the race under consideration, and typically only one of
these two parameters is used. In (very)
rare instances, however, the user might specify nonzero values for both
parameters. One such instance is the
testing of alternative models. In
another instance, nonzero values might be used for both parameters in the
situation in which accurate data were available separately for emigration and
immigration. In this case, the
emigration would be represented by a negative migration rate and the
immigration would be represented by a positive migration number. In most situations, accurate data will not be
available for emigration and immigration separately. Instead, estimates will be available for
total net migration (immigrants less emigrants), and the total net migration
may be expressed either as a net migration rate (if negative) or a net
migration number (if positive).
Although migration rates and numbers may be positive
or negative, it is highly recommended that positive net migrations be
represented by (positive) values of the net migration number and that
negative net migrations by represented by (negative) values of the net
migration rate. Because migration
rates are typically used in cases in which an area is losing population,
we shall sometimes refer to a migration rate as an emigration rate;
similarly, because migration numbers are typically used in cases in
which an area is gaining population, a migration number shall sometimes be
referred to as an immigration number.
This terminology may be confusing, however, since strictly speaking both
the migration rate and the migration number measure immigration
(migration into an area.
The rationale for the convention of using migration
rates for negative migrations (net population losses) and numbers for positive
migrations (net population gains) is both logical and practical. In the first instance, a country that is
gaining population through immigration (such as the US) may enforce numerical
limits on immigration, whereas population shrinkage due to emigration is less
subject to control and more logically represented as a percentage of the
country's remaining population. From a
practical viewpoint, large net positive immigration levels should definitely
not be used, since they quickly lead to absurdly high population
projections. As a general rule,
migration numbers should always be positive (representing net positive immigration)
and migration rates should always be negative (representing net positive emigration).
Under External Migration Option 1, the program first
requests:
ENTER 1 NET MIGRATION RATE(S) (ANNUAL, PER 1000, 8XXXX.XXX): ,
(to which the user might respond, for example,
-8.3
(ENTER) ),
and
ENTER 1 NET
MIGRATION NUMBER(S) (ANNUAL, 8XXXXXXXXX.): ,
(to which the user might respond, for example,
500000.
(ENTER) ).
As discussed above, typically at most one of these two
entries would be nonzero.
Under Option 2, the program requests ten migration
rates and ten migration numbers. (Note:
Since the format for the migration numbers is 8XXXXXXXXX., two data entries are
required, the first line consisting of eight numbers and the second line
consisting of two numbers.)
Note on Other Factors Included in External Migration
Changes in the size of a population of a specific race
may result from factors other than births, deaths, and net external
migration. Other factors that may
contribute to changes in the size of a population of a specific race include
changes in race declarations, changes in procedures, criteria, or categories
used to collect race data, and crossbreeding among races. Changes in the size of a population of a
specific race beyond those associated with births, deaths, and external
migration are referred to as "race transitioning."
In the DESTINY model, race transitioning is included
in external migration. For example, if
the net external migration of a population of a specific race over a particular
time interval is 1,000, this could refer to 1,000 immigrants and no emigrants;
or 4,000 immigrants and 3,000 emigrants; or no immigrants, no emigrants, and
1,000 births that are not classified as the race of the mother; or 1,000
individuals who declare their race differently at the end of the time interval
from what it was at the beginning of the time interval.
Under the convention that external migration includes
race transitioning, external migration may be defined simply as the total
amount of population change (for a particular race) net of births and
deaths. This convention not only
simplifies the model specification, but more importantly it simplifies the
problem of estimating values for the model input parameters. From available data, it is a simple matter to
estimate the population change net of births and deaths -- the problem of
attempting to decompose this quantity into a portion due to migration and a
portion due to race transitioning is formidable.
It is noted that the population change that occurs
over a time interval beyond that associated with specified birth and death
rates (or, more properly, with specified fertility and mortality rates) is not
limited to external migration and race transitioning. If the fertility or mortality rates change
from the specified values, the size of the population will differ from the
projected size associated with the specified values. While external migration may be a major
factor explaining why a future population differs from that projected for a
specified fertility and mortality rate, it is not the only factor.
Regional Populations
If the user entered "1" (or "0" or
blank) for the number of regions, the program will not ask for regional
populations. If any number greater than
one were entered, then the user must enter the total population of each
region. A separate set of regional
populations is required for each race being entered into the parameter file.
If regional structure is being incorporated into the
model, the program requests:
ENTER BASE-YEAR
POP'N BY REGION (8XXXXXXXXX.): .
The regional populations are entered with the same
format as the base-year populations by age and sex -- eight values per
entry. Of course, if there are fewer
than eight regions, then fewer than eight values will be typed. As an example, suppose that there are twelve
regions. In this case, two entries will
be required -- eight values for the first entry, and four entries for the
second.
The sum of the regional populations must equal the sum
of the base-year populations by age and sex.
If they do not, the program rejects the entered regional populations,
and requests the user to enter correct values.
The program then requests the regional populations for
the year ten years previous to the base year (same format as above). The sum of these regional populations must
equal the total population ten years prior to the base year. If they do not, they are rejected and correct
values requested.
Internal Migration (Including Allocation of External
Migration to Regions)
As remarked earlier, internal migration refers to the
redistribution of the population among the regions of the area, due to movement
of the residents from one region to another, to settlement of immigrants, and
to emigration. Under Option 0, or if
there are no regions in the model, there is no data entry.
If Internal Migration Option 0 is specified, the
population change of each region from one projection period to the next (due to
births, deaths, and external migration) is proportional to the current regional
population (of a particular race), for every race. In this case, any differences in growth rates
among the regions are solely due to differences in birth and death rates resulting
from different racial compositions of the regions. Whatever external migration was specified in
the preceding section is allocated to the regions of the model in proportion to
their populations (of the race under consideration). (Under Option 0, if there were but a single
race represented in the model, all regions would grow at the same rate.)
Under Option 1, the program represents internal
migration as the population change (number or rate per 1,000) net of births,
deaths, and external migration allocated proportional to the regional
population (of the race under consideration).
In other words, the internal migration parameters specify the average
annual amount of change or rate of change (per 1,000 population) in the
regional population beyond that attributable to births, deaths, and a
proportional allocation of external migration to the regions. As used in the DESTINY system, the term
"internal migration" hence includes not just interregional population
movements but also nonproportional allocations of
external migration to the regions.
If external migration is estimated as the population
change net of births and deaths, the regional internal migration amounts
will sum to zero over all regions (the regional internal migration rates
do not necessarily sum to zero, except by coincidence). The sum of the regional population changes
computed from the rates (by multiplying each regional rate by the regional
population) is not necessarily zero, although it should be close to zero. The program resolves this inconsistency
through the use of an adjustment procedure analogous to that discussed
previously in the section on external migration (under the option that permits
the entry of age/sex-specific external migration rates). With this procedure, changes in regional
populations due to internal migration are proportional to the user-specified
regional growth parameters. If the sum
of the regional population changes resulting from this procedure is not zero
(so that the population total is changed), all populations are proportionally
adjusted (scaled) to bring the total population back to the value prior to
application of the internal migration process.
The user may specify an internal migration rate and/or
an internal migration amount for each region.
As usual, it is recommended that a rate be used if the parameter value
is negative, and an amount be used if the parameter value is positive.
Unless accurate data on external migration are
available and race transitioning is negligible, it is recommended that external
migration be estimated as population change net of births and deaths, so that
the sum of the internal migration amounts is zero.
Under Option 1, the program requests:
ENTER n REGIONAL INTERNAL MIGRATION RATES (ANNUAL, PER
1000,
8XXXX.XXX): ,
where n denotes the number of regions. The user must specify one internal migration
rate for each region. The rate for a
region is the annual rate of population growth per 1,000 net of births, deaths,
and proportional allocation of external migration to the regions. The format is 8XXXX.XXX, and at most fourteen
regions are allowed, so that all numbers are to be entered as a single data
entry.
The program then requests:
ENTER n REGIONAL INTERNAL MIGRATION AMOUNTS (ANNUAL,
8XXXXXXXXX.): .
If more than eight entries are needed, more than one
line will be required for data entry.
The internal migration amount for a region is the average annual
population change net of births, deaths, and proportional allocation of
external migration to the regions.
If the convention of using rates for negative numbers
and amounts for positive numbers is followed, the user will be required to
enter rates for some regions and amounts for other regions, but only one of
these parameters will be nonzero for each region.
With the completion of the internal migration input,
the demographic data entry cycle is completed for one race, and the program
recycles to request the demographic data entry for the next race (if any.)
If the user indicated that no program-related data
were to be entered (by entering a "0" for the service system option
P7 in the Input Option Parameter section, then this input section is skipped by
the program. Otherwise, the data entry is
as follows.
Service-System Parameters
There are five service-system parameters,
corresponding to five subsections of the service-system data section of the
PARAM program:
S1: Number
of Target Populations (1-4)
S2: Service
Population Option (0,1, or 2)
S3: Number
of Services (0-10)
S4: Number
of Resources (0-7)
S5: Number
of Cost Categories (0-4).
The program requests entry of each of these
service-system parameters by means of five separate requests, as follows:
ENTER NO OF
TARGET POPULATIONS (1-4):
ENTER
SERVICE POPULATION OPTION (0,1, OR 2):
ENTER
NUMBER OF SERVICES (0-10):
ENTER
NUMBER OF RESOURCES (0-7):
ENTER
NUMBER OF COST CATEGORIES (0-4): .
After each of the preceding requests, the user types
the appropriate number, and depresses the ENTER key. For all but the second parameter, the nature
of the parameters is self-evident. For
the second parameter, the options are as follows:
o Option 0. There is no service population.
o Option 1. The service population is identical
to the target population.
o Option 2. The service population is
proportional to the target population.
The factor of proportionality may be less than or greater than
unity. That is, the size of the service
population may be less than or greater than the target population.
The five parameters S1-S5 determine how much data
entry follows. If any parameter is zero,
the corresponding data entry section and all succeeding data entry sections of
the service-system data section are skipped.
For example, if the five entries were 1, 0, 1, 1, and 1, then only
target population data would be accepted.
After the user enters the five service-system
parameters, the program requests the user to enter names corresponding to all
of the target populations, service populations, services, resources, and cost
categories that have been specified.
These requests are as follows:
ENTER NAME
FOR TARGET POPULATION NO i (8X):
ENTER NAME
FOR SERVICE POPULATION NO j (8X):
ENTER NAME
FOR SERVICE NO k (8X):
ENTER NAME
FOR RESOURCE NO m (8X):
ENTER NAME
FOR COST CATEGORY NO n (8X): ,
where i varies from 1 to the
number of target populations, j varies from 1 to the
number of service populations, k varies from 1 to the number of services, m
varies from 1 to the number of resources, and n varies from 1 to the number of
cost categories.
Note that in ordinary speech the service population and
the target population will often have the same name, e.g., the term
"elderly" could refer either to "all elderly persons," or
to "elderly persons served."
In giving names to these two populations (the target population and the
served population), however, it will avoid substantial confusion in the PROJ
printout if different names are used.
For example, the acronym ELDERLY could be used for the target
population, and the acronym ELD(SV) could be used to denote the served
elderly. Then, in the PROJ output, no
confusion will arise --for example, it will be clear that a crosstabulation
labeled "DISTRIBUTION OF ELDERLY BY AGE AND SEX" refers to the total
elderly population, not just the served elderly population.
Similarly, in naming services, resources, and costs,
use different labels, e.g., COUNSLNG for counseling services, COUNSELR for a
counselor (a resource), and COUNCOST or COUNSLR$ for the cost of counseling, so
that the PROJ printouts are unambiguously labeled. If the single word COUNSELR were used for all
three entities, the labels which PROJ prints out on the various tables would be
confusing.
The name may consist of any eight characters,
including blanks. For example, suppose
that there are two cost categories -- direct costs and administrative
costs. Names for these two cost
categories could be as follows:
DIR COST
and ADM COST ,
where the blank is typed using the space bar on the
console keyboard.
Each of the five data subsections of the Service
System Data section will now be described.
The five subsections are discussed in the following order:
o Service Parameters
o Resource Parameters
o Cost Parameters
o Target Population Parameters
o Service Population Parameters.
Although specification of the target population and
service population parameters would logically precede the specification of the
other service-system parameters, they are entered last, in order to permit
certain efficiencies in the program computer code.
Service Parameters
For each service population, the user must enter the
average number of service units of each type expended per case served per
year. By means of example, suppose that
there are two target populations, two service populations, three services, and
that the average numbers of service units are as follows.
Service Units
Service
Population Service Type /Case/Year
1. Child
Abuse 1. Counseling (COUNSLNG) 24.0 hrs.
(CH
ABUSE) 2. Physical Therapy
(PHYSTHRP) 0.0 hrs.
3. Day Care (DAY CARE)
200.0 hrs.
2.
Disabled 1. Counseling 12.0 hrs.
(DISABLED) 2. Physical
Therapy 80.0 hrs.
0.0 hrs.
In this case, the program would request:
SERVICE
POPULATION = CH ABUSE
ENTER
AVERAGE NO OF SERVICE UNITS (XXXXX.XXXX) PER CASE SERVED, FOR SERVICE TYPE = COUNSELNG:
.
The data entry in this case would be:
24. (ENTER) .
The program would then request:
SERVICE
POPULATION = CH ABUSE
ENTER
AVERAGE NO OF SERVICE UNITS (XXXXX.XXXXX) PER CASE SERVED, FOR SERVICE TYPE = PHYSTHRP: ,
to which the user would respond:
0. (ENTER) .
The program would repeat a similar request for service
type Day Care, and then make three similar requests for the service population
Disabled.
Note that the average number of service units
requested by the program is the average over all served clients in the
service population, over an entire year.
It is not the conditional average, given that the client
receives at least some of the service (this latter quantity would be much
larger).
Resource Parameters
For each service, the user must enter the average
number of resource units of each type required per service unit. It is emphasized that this parameter is the
average per service unit, not per case.
For example, suppose that there are two resource types (counselors and
contract services), and that the average number of resource units per service
unit are as follows.
Resource Unit
Service
Type Resource Type /Service Unit
1.
Counseling 1. Counselor (COUNSELR) .0005 cnslrs/hrs
(COUNSLING) 2. Contract Service
0.0
(CONT SVC)
2.
Physical 1. Counselor 0.0
Therapy 2. Contract
Service 25.0 cntrct
svc
units /
hour
3. Day
Care 1. Counselor 0.0
(DAY
Care) 2. Contract Service 30.0 cntrct svc
units / hour
In this example, it is assumed that the state does not
employ physical therapists or provide day care services. Instead, both physical therapy and day care
services are provided by outside contractors (service providers). In this case, the resource units are in fact
dollars. It is assumed that each
counselor works 2000 hours per year, so that the average number of counselors
(the resource) per counselor hour (the service) is (1 counselor)/(2000 hours of
service) = .0005 counselors per hour of counselor service.
The program first requests:
SERVICE
TYPE = COUNSLNG
ENTER
AVERAGE NO OF RESOURCE UNITS (XXXXX.XXXX) PER SERVICE UNIT, FOR RESOURCE TYPE =
COUNSELR: ,
to which the user responds:
.0005
(ENTER) .
The program next requests:
SERVICE TYPE = COUNSLNG
ENTER
AVERAGE NO OF RESOURCE UNITS (XXXXX.XXXX) PER SERVICE UNIT, FOR RESOURCE TYPE =
CONT SVC: ,
to which the user responds:
0.0 (ENTER)
.
The program then goes on to the next service type
(Physical Therapy), and asks for the average number of units of each resource
type. The same is then done for the
third service type (Day Care), and the Resource Parameter section is finished.
Cost Parameters
For each resource, the user must specify the average
cost (for up to four cost categories) per resource unit. It is emphasized that this is the average
cost per resource unit, not per client or per service unit. For example, suppose that two cost categories
are of interest -- state personnel costs and contract services costs -- and
that the average cost per resource unit are as follows:
Cost
Resource
Type Cost Category /Resource Unit
1.
Counselor 1. State Personnel $20,000.00/counselor
(COUNSELR) (DIR SV $)
2. Contract Service
0.00/counselor
(PUR SV $)
2. Contract Svc
1. State Personnel
0.00/contract
(CONTR
SV) service
unit
2. Contract Service $1.00/contract
service unit
Since the contact service units are actually dollars,
the number of dollars per contract service unit is 1.00.
The program requests:
RESOURCE
TYPE = COUNSELR
ENTER
AVERAGE COST (XXXXX.XXXX) PER RESOURCE UNIT, FOR COST CATEGORY = DIR SV $: ,
to which the user responds:
25000.
(ENTER) .
This question is repeated for the second cost category
(Contract Services), to which the user responds with the entry 0.00. The question is then repeated two more times
for the second resource type (Contract Services), completing the data entry for
the cost parameters.
Note that in the preceding example, the resource
associated with counseling services was defined to be a counselor, and the cost
was $20,000.00 per counselor (one year's salary plus overhead). We might just as easily have defined the
resource in this case to be a counselor-hour, in which case the cost would have
been $20,000.00/2000 = $10/counselor-hour.
Target Population Parameters
The program requires a set of incidences (or prevalences, as the case may be) for each target
population. Incidences (used in the case
of the occurrence of acute medical conditions or events such as prison
admissions) indicate the rate of occurrence of each type of condition in a single
year (not in a five-year period).
Prevalences (used in the case of chronic
conditions) indicate the proportion of the population that has each condition
at a point in time. Both rates
(incidences or prevalences) refer to the population,
e.g., an incidence of .01 signifies that 1% of the total population acquires
the condition defining the target population at some time during the year, each
year. Similarly, a prevalence of .01
signifies that 1% of the total population has the condition defining the target
population at any given point of time in the year. In the discussion that follows, we shall use
the term "incidence" or "rate," rather than the more
correct but cumbersome "incidence or prevalence." Note that incidences may exceed one in value
(since the average number of occurrences of a condition might exceed one per
person), but that prevalences (which refer to a
subset of a population) are less than or equal to one.
There are ten different ways in which the user may
enter incidences, depending on the level of detail desired. These ten ways are called
"stratifications." They are defined
as follows.
o ST1: A single rate is specified for the entire
popu- lation. (Strictly speaking, this case corresponds to
"no stratification.")
o ST2: A separate rate is specified for each age
category.
o ST3: A separate rate is specified for each sex
category.
o ST4: A separate rate is specified for each
race.
o ST5: A separate rate is specified for each age
x sex category.
o ST6: A separate rate is specified for each age
x race category.
o ST7: A separate rate is specified for each sex
x race category.
o ST8: A separate rate is specified for each age
x sex x race category.
o ST9: A separate rate is specified for each
region.
o ST10: A separate rate is specified for each
race x region category.
Which level of detail, or stratification, is selected depends
on two factors: what level of detail is present in available data, and what
level of detail is desired in the cross- tabulations of the PROJ
projections. For example, if the user
wants breakdowns of the population by race, and there are differences in the
incidence by race, then stratification option ST4 should be used.
Note that the level of detail of the crosstabulation projections should ordinarily not exceed
the level of detail of the input data.
For example, if a single incidence is specified for the entire
population, then projection cross- tabulations should not be specified by age x
sex x race, unless it is known that the incidence is in fact the same for all
age x sex x race categories.
The user will usually be able to find reasonably good
national-level data which indicates incidences for the general population, so
that option ST1 may be used.
Furthermore, for many target populations, incidences by age, by sex, by
race, or by combinations (e.g., sex x race) are available. Incidences are generally not available by age
x sex x race, except for conditions that have been studied rather
extensively. If several low-dimensional crosstabulations are available (e.g., by age, by sex, and
by race), procedures are available for statistically estimating a
higher-dimensional crosstabulation (e.g., age x sex x
race) from these lower-dimensional crosstabulations.
There are two different ways in which incidences are
entered to the program. For options ST1,
ST3, ST4, and ST7, the program instructs the user to enter incidences for each
and every stratum "cell" (combination of levels of the variables of
stratification), in a particular order specified by the program, and also
specified on the data entry forms of Appendix B.
For example, suppose that the following incidence
matrix applies:
Race
W O
M .02 .04
Sex
F .03 .05
That is, the user wishes to specify incidences by sex
and race (option ST7). In this case, the
data entry is as follows.
First, the program prints out the following on the
video screen:
THE
FOLLOWING TYPES OF STRATIFICATION ARE AVAILABLE:
1: NONE
2: AGE
3: SEX
4: RACE
5: AGE X
SEX
6: AGE X
RACE
7: SEX X
RACE
8: AGE X
SEX X RACE
9: REGION
10: REGION X
RACE
ENTER TYPE
OF STRATIFICATION (1-10): .
Since stratification type 7 is desired, the user
enters
7 (ENTER) .
The program then requests:
ENTER 4
INCIDENCE PREVALENCE RATES (8X.XXXXXXXX): .
In accordance with the sequence specified by the data
entry form of Appendix B, the user must enter the four rates as follows:
.02,.03,.04,.05 (ENTER) .
The order in which the entries are made in the data entry
forms is as follows:
Increment
age, followed by sex, followed by race.
Hence, in the preceding example, two age values were
input for the first race, followed by two values for the second race. Increment age in increasing order of age, sex
by male followed by female, and races in the order in which they were entered
in the PARAM data entry program (and are displayed by the CHECK program).
The preceding example illustrates the data entry
procedure for options ST1, ST3, ST4, and ST7.
For the other options, ST2, ST5, ST6, ST8, ST9, and ST10, the user must
specify up to nine different rates, and then specify, for each stratum cell,
which rate applies. (This approach is
used for all stratification options in which the total number of stratum cells
exceeds nine.) For example, suppose that
the option ST2 is used, i.e., stratification is desired by age. Suppose that the incidences are as follows:
Age
Category Incidence
0-4 0.0
5-9 0.0
10-14 .01
15-19 .05
20-24 .02
25-29 0.0
30-34 0.0
35-39 0.0
40-44 0.0
45-49 0.0
50-54 0.0
55-59 0.0
60-64 0.0
65-69 0.0
70-74 0.0
75+ 0.0
In this example, the program will request:
ENTER TYPE
OF STRATIFICATION (1-10): ,
to which the user will respond:
2 (ENTER) .
The program will then request:
ENTER 9
INCIDENCE/PREVALENCE RATES (8X.XXXXXXXX):
to which the user will respond:
0.0,.01,.05,.02 (ENTER) .
The user enters four different rates, since there are
only four different rates specified in the table shown above. There is no need to explicitly enter five
additional zeros; by depressing the ENTER key after only four values, the next
four values will automatically be taken as zeros. Since the program requires that nine values
be entered, but the format only allows for the entry of eight values at a time,
the ENTER key must be depressed a second time, to allow for the entry of the
ninth value (a blank, in this example).
In an example in which nine different values were entered, eight would
be entered on the first line (followed by ENTER), and one would be entered on
the second line (followed by ENTER.)
The program next requests:
ENTER 16
INDICES (ONE FOR EACH AGE COHORT), EACH OF VALUE 1-9 (16X): ,
to which the user may respond either with:
1,1,2,3,4,1,1,1,1,1,1,1,1,1,1,1 (ENTER) ,
or
1123411111111111
(ENTER) .
The i-th index number in
this list indicates which of the four entered rates applies to the i-th age category.
For example, the index "2" in the third position of the index
list signifies that the second rate (.01) applies to the third age category
(ages 10-14).
There are limits on the number of stratifications of
each type (in addition to the overall limit of four target populations in
all. The following table specifies the
maximum number of stratifications of each type:
ST1 4
ST2 4
ST3 4
ST4 4
ST5 4
ST6 4
ST7 4
ST8 4
ST9 4
ST10 4
From this table, we see that the incidence rates for
up to four target populations can be specified using stratification type ST2
(stratification by age), but only one target population can be specified using stratification
type ST8 (stratification by age, sex, and race).
The user is requested by the program to enter
incidences for each of the target populations specified.
Service Population Parameters
With regard to service populations, there are three
different cases (corresponding to the three options of the Service-System
Parameter S2). If a "0" is
specified for the value of Service-System Parameter S2, then no service
population data are requested, and the Service System Parameter section is
skipped. If S2 = 1, then the total
target population is taken as the service population, i.e., the service
population is all of the persons in the target population. If S2 = 2, then the service population is a
proportion of the target population. The
factor of proportionality may be less than or greater than one. These factors, called service ratios,
may vary by the same variables of stratification (age, sex, race, or region) as
were described for the incidences/prevalences of the
Target Population Parameter section, and the procedure and formats for the data
entry of the service ratios are exactly the same as for the Target Population
Parameters.
For example, suppose that there is only one target
population under study, and that a flat 10% of the target population is served,
regardless of age, sex, or race, then the user would specify option ST1 (no
stratification), and enter a "1" when requested to enter the type of
stratification. The program would then
prompt for the rate, which would be entered as ".1" (format
X.XXXXXXXX).
Note that the services, resources, and costs do not
vary by demographic characteristics of the served population. Any dependencies of service on age, sex,
race, or region must be reflected in the definition of the target population or
the service (served) population. Because
of this restriction, it may be desirable (if services, resources, or costs vary
by demographic characteristics of the person served) to define a service
population as a number of person-years or a number of occurrences of a
condition, rather than a number of individuals (subset of the target
population).
This completes the data entry for the PARAM program.
A Note on Updating a Parameter File
When creating a new parameter file from an existing
parameter file, it is often the case that the user retains much of the old data
in the new file, without change. For
example, the user may wish simply to append some target population data to an
existing demographic-data parameter file.
In this case, the program will prompt the user many times with a request
such as:
ENTER 1 TO
CHANGE DATA, 0 OTHERWISE: .
The response in most cases will be:
0 (ENTER) .
To save time, there is no need to actually enter the
"0" -- the user may simply depress the ENTER key, and the program
will automatically interpret that a "0" was entered. In this way, the user may very quickly run
through those portions of the file which are not to be changed (such as the
demographic parameters, in the example specified.)
The CHECK program has two uses. Its main use, described in this chapter, is
to print out the contents of a parameter file.
A second use, to adjust the service parameters of a parameter file, is
described in Chapter V.
After using the PARAM program to enter the parameters,
it is important to review them with a CHECK run. It is easy to enter a wrong digit, or to
invert two digits, in entering the data to PARAM. Also, if a string of data were entered using the
wrong format, the data values will be recorded wrong in the parameter
file. For example, suppose that a series
of fourteen numbers were required for entry by PARAM, using format 8F10.0, but
the user entered ten entries on the first line and four on the second line
(instead of eight entries on the first line and six on the second line). In this case, the last two entries on the
first line would be ignored by the program, resulting in an incorrect data
entry. The user would not be aware of
such an error until running the CHECK program, when it would be seen that two
of the entries had been lost.
In addition to using CHECK to review new data input,
it can be used to obtain a permanent hard-copy record of the contents of the
parameter file. The reason for doing
this is that the PROJ program does not print out any parameters -- it prints
only projections (or summaries of the base-year data). A CHECK printout of the parameter file should
be attached to the DEST printout, so that the analyst can be certain of the
parameter values to which the PROJ run corresponds. The parameter file name is printed at the
beginning of both the CHECK and PROJ printouts, for ready comparison.
The CHECK program is executed by typing CHECK at the
MS-DOS prompt. The first request the
CHECK program makes is:
ENTER 0 TO
PRINT EXISTING PARAMETER FILE, 1 TO INPUT NEW SERVICE-SYSTEM PARAMETERS FROM
SERVICE-SYSTEM ADJUSTMENT FACTORS:
,
to which the user responds:
0 (ENTER) ,
in order to obtain the desired printout.
The program's next request is:
ENTER NAME
OF PARAMETER FILE (12X): .
The user should enter the name (a valid MS-DOS file
name) exactly as he defined it in the PARAM run. For example, if the file name is AZ03CS.DAT,
the user responds with:
AZ03CS.DAT
(ENTER) .
The program then prints the parameter file. The user may direct the output to the video
monitor, the printer, or to a file named CHECKOUT.FIL .
The PROJ program computes projections based on the
parameter values in the parameter file.
The PROJ program is executed by typing PROJ at the MS-DOS prompt. After the program begins execution, the user
specifies the names of the parameter files, the number of five-year periods to
project, and the amount of printed output desired.
After printing out a copyright notice on the video
screen and on the line printer, the PROJ program's first request is:
ENTER NAME
OF PARAMETER FILE (12X): ,
to which the user responds with entry of the name that
was specified in the PARAM program run which created the parameter file, e.g.,
AZ803CS.DAT . The PROJ program prints
out (on the line printer) the name of this file, the file header, and the base
year.
The program then asks the number of five-year periods
to project. This number must be between
0 and 10. If a zero is entered, the
program will analyze the base-year data, but not construct any
projections. The number of years to be
projected is five times the entry, e.g., if a "3" is entered, then
the program will project up to fifteen years into the future. The number specified by the user is printed
by the line printer. The video request
is:
ENTER NO OF
FIVE-YEAR PERIODS TO PROJECT (0-10): .
(Note: If the user enters "1," after the
number of periods to project, the program will print out all of the
cohort-specific survival probabilities.
Since these quantities are of limited interest in many applications, the
program does not prompt the user concerning their printout. If three five-year periods are to be
projected, and the survival probabilities are desired, the data entry is:
3,1 (ENTER)
.)
Next, the program prints the following message:
THE
FOLLOWING TABLES OR CROSSTABULATIONS ARE AVAILABLE:
1: TOTAL
2: AGE
3: SEX
4: RACE
5: AGE X
SEX
6: AGE X
RACE
7: SEX X
RACE
8: AGE X
SEX X RACE
9: REGION
10: REGION
X RACE
SPECIFY
CROSSTABS DESIRED (10 NOS, 0 OR 1, FORMAT 10X): .
This prompt allows the user to specify which crosstabulations he wants for the base year. The program will repeat this request for each
five-year period, so that different crosstabulations
may be specified for each five-year projection period.
The user answers this request by typing ten numbers,
each 0 or 1. If the i-th
number of this ten-tuple is a 1, then the i-th type of table or crosstab
will be printed out. For example, if
only a crosstab of sex x race is desired for the base
year, the user would type:
0000001000
(ENTER) .
If a table by age is also desired, the user would
type:
0100001000
(ENTER) .
If the user does not select any tables or crossbulations, then the analysis proceeds to the next
projection period. Otherwise, the
program next requests:
ENTER 1 TO
SKIP SERVICE-SYSTEM ANALYSIS, 0 OTHERWISE: .
If the user enters a 1 in response, the program will
print out only demographic information, and not any service-system-related information
(on the target populations, service populations, services, resources, or
costs). If a 0 is entered, a full
printout (with both demographic and service-system data) will be done. After responding to this request, the line
printer then prints out the crosstabulations that
were requested by the user.
The program then prints the following information and
request on the video screen:
PROJECTION
PERIOD NO 1
YEARS: 19XX
TO 19XX ,
and repeats the request for the user to specify which crosstabs are desired, for the first five-year projection
period.
After the user specifies the desired crosstabs, the program then requests:
ENTER 1 TO
SKIP SERVICE-SYSTEM ANALYSIS, 0 OTHERWISE,
to which the user responds 0 or 1, as desired. Next, the program requests:
ENTER 0 TO
PRINT 5-YEAR PROJECTIONS, 1 TO PRINT 1-YEAR PROJECTIONS: .
If the user specifies a 0, the program will print out
the projection for the fifth year out.
If the user specifies a 1, the program will print intermediate years,
and prompt the user to specify the intermediate years for which printouts are
desired with the following request:
ENTER WHICH
YEARS TO PROJECT (5 INTEGERS, 0 = NO, 1 = YES, FORMAT 5X): .
The user enters five numbers, each 0 or 1. If the i-th number
is a 1, then a projection will be printed out for the i-th
year. For example, if the user enters
11111, then the program will print out projections for all five years. These intermediate-year projections are
computed by linear interpolation between the results for two adjacent five-year
projection periods.
The program then proceeds to print out all the
requested crosstabulations for the specified
years. After completion of this
printout, the program goes on to the next five-year period (if any), repeating
the requests for the user input described above for each five-year period.
The user may direct the output to the video terminal,
a printer, or a file named PROJOUT.FIL .
The service, resource, and cost models which are
incorporated into the PROJ program are very simple in concept -- they are
linear models involving small numbers of parameters. Although these models are particularly
well-suited to investigation of the impact of making marginal changes in a
service system, it is unlikely that they will produce exactly the same
estimates of service levels, resource levels, and cost levels, that are
observed in real life -- the actual system will be far more complicated.
After the user has specified the target population,
service population, service, resource, and cost models in terms of the
parameters available in the PARAM program, the PROJ program should be run for the
base year to see how closely the target population levels, service population
levels, service levels, resource levels, and cost levels are to known,
observable, base-year amounts. They will
likely differ somewhat. If the
differences are small, the user may proceed to make projections with PROJ. If some of the difference are substantial,
however, the user should reexamine the parameter values to make certain that
they are correct. Once any major
discrepancies are resolved, and the user is satisfied that the parameter values
are correct, there will still probably remain some minor discrepancies between
the actual base-year amounts and the PROJ base-year amounts.
At this point, the user has a choice to make. If the differences are not significant from a
substantive point of view, he may proceed directly to making PROJ runs. Alternatively, he may choose to adjust the
parameter values so that the PROJ base-year levels of the target populations,
service populations, services, resources, and costs match the actual base-year
levels exactly. If the analyst is
interested in estimating the cost or service changes that will occur if
some change is made in the service system, then minor discrepancies (between
PROJ base-year levels and actual base- year levels) in the absolute level are
not important. In other situations,
however, the user may be interested in estimating the actual level of some
quantity (rather than a relative change).
In such cases, it is best if the base-year levels computed by the PROJ
program are exactly matched to the actual base-year values. This matching procedure is called model
calibration. It is similar to the
Deming-Stefan statistical adjustment procedure ("raking"), or the
"ratio estimation" procedure of sample survey analysis. The user can accomplish this match by
adjusting the various system parameters (target population incidences, service
population, service ratios, service parameters, resource parameters, and cost
parameters), and updating the parameter file with a PARAM run. Using PARAM solely to adjust service-system
parameters is somewhat cumbersome, however, since the program first cycles
through all of the demographic parameters and data, none of which changes. The CHECK program, on the other hand, can be
used to quickly incorporate adjustments into the service-system model
parameters, without having to run through all of the PARAM demographic
parameter and data cycles.
The CHECK program allows the user to specify an
adjustment factor, or adjustment ratio, for each target population, service
population, service, resource, and cost total that the PROJ program computes
and prints out. These adjustment factors
are the ratio of the actual (observed) base-year level of each quantity to the
base-year level estimated by PROJ. The
CHECK program uses these adjustment factors to create a new parameter file
containing all of the same demographic information as the original file, but
corrected service-system parameters in place of the old service-system
parameters.
Suppose, for example, that there is a single target
population, service population, service, resource, and cost, and that the
following actual-base-year and PROJ-base-year estimates are observed.
Actual PROJ
Base-Year Base-Year Ratio
Value Value = Actual/PROJ
Target
Population No. 1 5,362 4,897 1.095
Service
Population No. 1 2,148 2,099 1.023
Service No.
1 317 246
1.289
Resource No.
1 117 122 .959
Cost No.
1 33,976 38,943 .872
The last column of the table contains the adjustment
factor, which is the ratio of the actual base-year values to the values
computed by PROJ for the base year. The
CHECK program requests the user to enter these adjustment factors. These factors are used to modify the
service-system parameters of the parameter file, such that when the next PROJ
run is made, it will match the base-year values exactly. This parameter adjustment procedure is much
faster than the procedure of adjusting the service-system parameters through
another run of the PARAM program, which allows the user to modify all
parameters, both demographic and service-system-related.
In order to use the CHECK program to adjust the
service system parameters, the user proceeds as follows. As usual, the program is begun by typing
CHECK at the MS-DOS prompt. In response
to the first request made by CHECK,
ENTER 0 TO PRINT EXISTING PARAMETER FILE, 1
TO IMPUTE NEW SERVICE-SYSTEM
PARAMETERS FROM SERVICE-SYSTEM ADJUSTMENT FACTORS: ,
the user responds with the entry:
1 (ENTER) .
The program then responds with:
ENTER NAME
OF OLD PARAMETER FILE (12X): ,
to which prompt the user responds with the name of the
existing parameter file, which contains the parameters to be adjusted, e.g.,
AZ803CS.DAT
(ENTER) .
The program then request:
ENTER NAME
OF NEW PARAMETER FILE (12X): ,
to which the user responds with the entry of a
different (unused) file name, e.g.,
AZ03CTS2.DAT (ENTER) .
The program then instructs the user to enter one
adjustment factor for each target population, service population, service, resource,
and cost total. For example, for the
target population totals, the program requests:
ADJUSTMENT
FACTORS FOR TARG POP...
ENTER
ADJUSTMENT FACTOR (X.XXX) FOR nnnnnnnn: ,
where nnnnnnnn denotes the
name of the first target population (e.g., ELDERLY, or DISABLED). The user would respond with entry of the
appropriate data. In the example
presented in the above table, this would be:
1.095
(ENTER) .
In similar fashion ratios are entered for all of the
target populations, service populations, services, resources, and costs
included in the model. When used to
adjust service-system parameters, the CHECK produces all of the same printout
as when it is used simply to print out a parameter file. In addition, however, it also prints out the
adjustment factors, and both the old and new values of the service-system
parameters.
Projection Objectives This and the
next several chapters of this manual present a number of examples of
applications of the DESTINY program package.
The purpose of the examples are several -- to show in detail how to
obtain the data required by the model, to illustrate how to use the model, and
to provide an indication of the accuracy of the model projections. For the examples, the model will be set up
with data from 1980 and before, and used to project up to 1990.
This chapter and the following one present examples which illustrate in detail the use of the DESTINY
package to make projections of the
This chapter addresses a "single-race"
model, in which all races are combined.
The following chapter addresses a three-race model.
DESTINY projections may be disaggregated to the same
level of disaggregation as is represented in the
population input data. In the present
chapter, the population input data are disaggregated by age and sex, and the
projections may be disaggregated by age and sex. In the following chapter, the population
input data are disaggregated by age, sex, and race, and the projections may be
disaggregated by any combination of those three variables. In addition to disaggregation
by age, sex, and race, later chapters will illustrate disaggregation
by region and by region and race.
In order to permit an assessment of the reliability of
the DESTINY projections, the projections in this example will be based on
demographic data for the base-year of 1980 that were available in 1982. The DESTINY projections for the year 1990
will be compared to US Census data for 1990.
Data Sources A primary objective of the DESTINY package is
to enable projections to be made using readily accessible demographic data, available
in many libraries. Examples of such
sources are US Census publications (available decennially), the Statistical
Abstract of the United States (available every year), the Vital
Statistics of the United States (natality and
mortality volumes available each year), and the County and City Data Book
(supplement to the Statistical Abstract, various years). A major advantage of the Statistical
Abstract is that it is published regularly and contains quite recent
data. Similar publications are available
for each state. All of the demographic
data used in the examples presented in this document is available from such
sources.
The demographic data required for the present example
are available from the following three publications:
o CP80 Census
of Population, Supplementary Report PC80-S1-1, Age, Sex, Race, and Spanish
Origin of the Population by Regions, Divisions, and States: 1980. Bureau of the Census, US Department of Commerce (for sale by the
Superintendent of Documents,
o VS78: Vital
Statistics of the
o SA81: Statistical
Abstract of the
These three publications will be referred to in the
remainder of this chapter as CP80, VS78, and SA81, respectively. CP80 provides a crosstabulation
of the population by age, sex, and race, where the age categories are in
five-year intervals up to age 85, and 85+.
VS78 provides vital statistics data (birth rates, death rates, infant
mortality rates, total fertility rates, fertility age distributions, and life
expectancy at birth), also by age, sex, and race. SA81 population data are not sufficiently
detailed for use as DESTINY input, since the five-year categories go only to
age 65, and 65+. (DESTINY requires
population by five-year age intervals up to age 75, and 75+.)
All three publications present data not only for the
Since the DESTINY package is concerned with population
projections, the user should enter parameter values corresponding to his
beliefs about the demographic situation in the future. It is not necessary that the demographic
parameter values mirror the values experienced in recent history. Unless the user is performing a
"what-if" exploratory analysis or sensitivity analysis, however, the
input values would normally correspond to recent history. For this reason, much of the discussion of
this chapter is concerned with the identification of estimates derived from
historical data. If the user believes
that the future demographic situation will depart in some fashion from recent
history, however, the input values will differ from the historical values.
When using historical values of parameters, the user
should normally use parameter values corresponding to the base year, unless
there is substantial year-to-year variability in the parameter values. In this case, the user should use an average,
such as a five-year average value, as the specified value. If state or local-area data are suspect
because of small sample sizes or rapidly changing demographic trends, it would
probably be preferable to use more stable regional or national parameter
values, rather than the state or local-area values.
The example presented here does not describe every
line of input data entered into the PARAM, CHECK, and PROJ programs. Instead, the required data are described. The user can readily see the order of input
of the parameters from the CHECK printout, which closely follows the data entry
order of the PARAM program.
Note on Migration Data Prior to specifying
the data for the desired run, it is necessary to make a few remarks about
migration data. Published migration data
refer to legal migration, and the actual migration in recent years in the
It may be asked why the CHECK program cannot be used
to provide migration estimates from the two-race data. The CHECK program estimates the difference
after ten years between the total population and the population level
associated with natural increase (population growth due to births and deaths,
excluding migration). In a single-race
model, this difference is a reasonable estimate of the amount of migration over
the ten-year period. In a multi-race
model, however, this difference is a poor estimate of migration (by race). There are two main reasons for this. First, race data are very subjective: they
are based on the respondent's declaration of race. Ambiguous responses may be provided to race
questions, or a respondent's race declaration may differ in time. In addition, the criteria and procedures for
making race classifications have changed over the years. Second, over a period of years the racial
composition of a multi-race population becomes intermixed, because of
cross-breeding. A third source of error
is associated with the fact that the DESTINY program estimates net
migration. If the racial composition of
emigrants and immigrants is different, the racial composition of the resident
population will change over time even if there is no net migration.
Input Option Parameters
In running the PARAM program, the name US801.DAT was
given to the parameter file, and the base year was identified as 1980. The file header, "US Resident
Population," was used. The seven
Input Option Parameters were as follows:
P1: Number of
races = 1
P2: Number of
regions = 1
P3: Demographic
Parameter Option = 1 (i.e., the demographic parameters are to be the same for
all ten five-year projection periods)
P4: Life Table
Option = 1 (i.e., the survival probabilities for the population will be
determined by the Infant Mortality Rate, rather than by the Expectation of Life
at Birth)
P5: External
Migration Option = 1 (i.e., a single migration rate and/or migration number
will be specified, to be used for all projection periods)
P6: Internal
Migration Option = 0 (no regions are specified, so there is no internal
migration)
P7: Service
System Option = 0 (i.e., no service system parameters are included in the
model).
The program next requests the names of the races. The name "All" was entered.
Since the present model includes but a single race,
just one complete set of demographic data is required. These data are given in the paragraphs that
follow.
An issue that arises immediately is how the values for
the model parameters shall be determined.
In some instances (e.g., base-year population), a base-year value is
requested by the model. In other cases
(e.g., infant mortality rate for the first projection period), it is not
obvious what value should be used -- the base year value, the average value for
the preceding five years, the average value for the preceding ten years, or the
extrapolation of a trend of five-year averages.
In general, the values specified for the first (or later) projection
periods should be the values the user considers most likely for those periods,
whether these are continuations of current values or the results of extrapolations. In general, it is better to use multi-year
averages for estimates of the future values of parameters rather than the
base-year value, because of the significant amount of variability in
single-year values for many demographic parameters.
For the present example, we shall generally use the
average value of a parameter for the five years preceding the base year, as the
value for the first and later projection periods.
Total Fertility Rate
Total Fertility Rates for the
Total Fertility Rates (TFRs)
are also presented on page I-9 of VS78, in Table I-6, entitled, "Total
Fertility Rates and Birth Rates by Age of Mother and Race: United States,
Specified Years 1940-55, and Each Year 1960-1978." The SA81 data are more recent than the VS78
data (i.e., for year 1979 vs. 1978).
Fertility Age Distribution
The Fertility Age Distribution for the total
Birth Rate
Age
of Mother per 1000 Women
10-14 years 1.2
15-19 53.4
20-24 115.7
25-29 115.6
30-34 61.8
35-39 19.4
40-44 3.9
45-49 .2
Total 371.2
TFR x 1000 (Tot x 5) 1856.
The Fertility Age Distribution data do not vary much
from year to year, and so the single-year (1979) data were used rather than
multi-year averages.
The PARAM program accepts a Fertility Age Distribution
(FAD) for only six age categories, i.e., for ages 15-44, rather than for the
eight categories presented above.
Combining the two end age categories of the above table with the adjacent
age group makes a very small difference in the FAD, and yields the following
table:
Birth Rate
Age of
Mother per 1000 Women Percentage
15-19 54.6 .147
20-24 115.7 .312
25-29 115.6 .312
30-34 61.8 .166
35-39 19.4 .052
40-44 4.1 .011
Total 371.2 1.000
TFR x
1000 1856.
(Total x 5)
Note that the value 371.2 (the sum of the birth rates)
is equal to the Total Fertility Rate of all
The VS78 source (the same table in which the TFR is
presented) provides the FAD for 1978 (a year older than the SA81 source).
Infant Mortality Rate
Infant Mortality Rates are found on page 73 of SA81,
in Table 111, entitled, "Infant, Maternal, and Neonatal Mortality Rates,
and Fetal Mortality Ratios, by Race: 1940 to 1978." The average of the values for years 1975-78
is 14.80. (Mortality data are also
available from VS78 (Volume II, Part A), but the SA81 data are more recent.)
(Had a "2" been specified for the Life Table
Option parameter (Input Option Parameter P4), it would be necessary to enter
the Expectation of Life at Birth instead of the Infant Mortality Rate to the
PARAM program. These values are found on
page 69 of SA81, in Table 105, entitled, "Expectation of Life at Birth:
1920 to 1979." The average of the
values for years 1975-79 is 73.12. Life
expectancy data are also available in VS (Volume II, Part A), in Table 5-1,
entitled, "Abridged Life Tables by Color and Sex:
Base-Year Population by Age and Sex
Base-year population data by age and sex are published
in CP80. SA81 also contains population
data, but these data are not usable as DESTINY input since the age categories
above age 65 are combined.
The 1980 resident population data published in CP80
are presented in the table which follows.
Age Male Female
0-4 8,360,135 7,984,272
5-9 8,537,903 8,159,231
10-14 9,315,055 8,925,864
15-19 10,751,544 10,410,123
20-24 10,660,063 10,652,494
25-29 9,703,259 9,814,413
30-34 8,675,505 8,882,452
35-39 6,860,236 7,102,772
40-44 5,707,550 5,960,689
45-49 5,387,511 5,700,872
50-54 5,620,474 6,088,510
55-59 5,481,152 6,132,902
60-64 4,669,307 5,416,404
65-69 3,902,083 4,878,761
70-74 2,853,116 3,943,626
75+ 3,547,402 6,419,145
Total 110,032,295 116,472,530
Grand Total 226,504,825
Crude Birth Rate for Base Year
From SA81, Table 85, the value for 1979 is seen to be
15.9. (Although 1979 is not the base
year (1980), it is the latest year available, and is a suitable proxy for the
1980 value.)
Crude Death Rate for Base Year
From SA81, Table 108, the value for 1979 is seen to be
8.7.
Infant Mortality Rate for the Base Year
Table 111 of SA81 provides the value of 13.8 for 1978.
Population Ten Years Prior to Base Year
The next data element required is the population ten
years prior to the base year. This data
item is available from numerous tables of SA81, such as Table No. 29, page 26:
"Resident Population, by Age, Sex, and Race: 1960 to 1980." The 1970 population is 203,302,031. (Note: The figure 203,302,031 is a revised
figure, due to corrections for errors found after the tabulations of SA81 were
done. The figure 203,235,000 appears in
many of the tables of SA81.)
Average Crude Birth Rate for the Ten-Year Period Prior
to Base Year
From SA81, Table 85, the average for years 1973-79 is
seen to be 15.14.
Average Crude Death Rate for the Ten-Year Period Prior
to Base Year
From SA81, Table 108, the average for years 1973-79 is
seen to be 8.96.
Average Infant Mortality Rate for the Ten-Year Period
Prior to Base Year
From SA81, Table 111, the average for years 1972-78 is
seen to be 16.08.
External Migration
The final demographic data required by the program are
migration parameters. Migration data for
the
Because of the problems inherent in published
immigration figures, it is better to estimate net migration directly from
available data on crude birth rates, crude death rates, and the population
ten-year growth rate. The procedure is
illustrated below.
First, we shall derive an estimate of the annual
population change net of births and deaths.
For a single-race model, the population change net of births and deaths
is due to migration. There are two ways
to proceed, depending on whether it is desired to represent migration as a rate
or a number. As discussed earlier, if
the net migration is positive (i.e., the number of immigrants into the country
exceeds the number of emigrants out of the country), it is represented as a
migration number, and if the net migration is negative, it is represented as a
migration rate. The following will show
the procedures for estimating migration both ways (as a rate and as a number),
but the migration number will be used in the model specification, since the net
migration is positive.
In terms of the annual birth rate, death rate, and
migration number, an approximate expression for the population in year
t+1 as a function of the population in year t is:
pt+1 = (1+b-d)pt + M
where
pt = population in year t
b = crude birth rate
d = crude death rate
M = annual (net) migration number,
and all of the parameter values represent average values
over the ten-year period prior to the base year.
Solving this equation for M in terms of p10
and p0 yields the following:
M = (p10 - p0(1+b-d)10)(b-d)/((1+b-d)10-1)
.
Substituting b=.01514, d=.00896, p0=203,302,031,
and p10=226,504,825 yields the estimate:
M = 1,000,075.
That is, the average net annual number of immigrants
per year is estimated to be M = 1,000,075, which is about double the legal
immigration published in SA81, Table 128.
This is about 5 per thousand population per year. This level is more than double the legal
migration rate of 2 per thousand population per year. (The legal net migration rate would be
even less.) (A certain amount of the net
migration amount estimated above corresponds to a decrease in the Census undercount
from 1970 to 1980, and changes in racial classification procedures between 1970
and 1980.)
The estimated 1,000,075 is an estimate of migration
(including race transition) under the assumption that the birth and death rates
of the population are as specified.
The figure 1,000,075 may be entered to the PARAM
program as the estimate of the annual migration number. The annual migration rate is entered as zero
(since migration is specified either by the migration number or the migration
rate, but not both).
As was mentioned, migration may be represented either
as a number (as above) or as a rate. If
migration is represented as a rate, the formula for the population at time t
is:
pt+1 = (1+b-d+m)pt ,
where all of the symbols introduced earlier are defined
exactly as before, and
m = annual net migration rate.
Solving this equation for m in terms of p10
and p0 yields:
m = (p10/p0).1 -1 - b + d.
Substituting b=.01514, d=.00896, p0=203,302,031,
and p10=226,504,825 in this formula yields the estimate:
m = .004769,
or 4.686 per 1,000.
(Note that this is just slightly different from the approximate value
M/(average of populations for base year and ten years previous) = 1,000,075
/(.5(203,302,031+226,504,825) = 4.654 per 1,000.)
As discussed, since the net migration into the country
is positive, the migration number, M = 1,000,075, will be entered into the
PARAM program, and the migration rate will be specified as zero (not as
4.654).
The CHECK program performs the computations required
to determine both M and m. As an
alternative to performing the computations by hand, zeros may be specified
initially as the values for the migration number and rate (in the PARAM input),
and the CHECK program may be run to obtain the preceding estimates. The PARAM program may then be rerun to change
the initial value of zero to the estimated value (the migration number, M, if
the net migration is positive, or the migration rate, m, if the net migration
is negative).
Note that the net migration estimate derived for use in
the single-race model of this chapter will be used to derive net migration
estimates for use in the multi-race model of the next chapter.
This completes the data specification for the
construction of the file US801.DAT.
The output of a CHECK run of the file US801.DAT is
shown in Listing 1 (in Appendix D). The
program first prints out all of the input data.
A review of Listing 1 reveals that all of these input data are as
described above, with the exception of the population figures, which do not
agree past the seventh digit. This minor
discrepancy results from the fact that the computer on which the CHECK run was
made is precise only to seven digits.
After printing out the input data, the program then proceeds to print
out additional information, which can help the user assess the validity of the
input data.
The program prints out the expectation of life at
birth (73.96 years) corresponding to the infant mortality rate specified for
the first projection period (14.80 deaths per 1,000 live births). (Had the user specified a life expectancy at
birth as the parameter for selecting the life table used by the model, the
program would have printed out the corresponding infant mortality rate.)
In general, if the user enters the infant mortality
rate to specify the life table (i.e., Life Table Option 1), he should examine
the expectation of life at birth for reasonableness. Alternatively, if the expectation of life at
birth is specified, (i.e., Life Table Option 2), he should examine the infant
mortality rate for reasonableness.
If requested by the user (at the beginning of the
CHECK run), the CHECK program prints out a table of survival probabilities by
age and sex.
After printing out the input data, the program
provides a number of additional estimates.
The first is an estimate of the Total Fertility Rate estimated from the
base-year birth rate and the base-year population distribution. This estimate, 1.833, is seen to be quite
close to the value specified for the first projection period, 1.810.
The program estimates the general fertility rate
(birth rate per 1,000 females of ages 15-44) as 68.18. This compares with the value of 68.5 found in
Table 85 of SA81.
Next, the program estimates the net migration. As discussed above, the estimated annual net
migration number is 1,000,075, and the corresponding annual net migration rate
is 4.686 per 1,000.
The approximate projected population growth rate
corresponding to the model parameters specified for the first projection period
is 9.62 per 1,000. For the previous ten
years, the population growth rate per 1,000 was 10.87.
The CHECK run reveals no unusual features in the
data. The estimated base-year and
projected total fertility rates are similar, and the projected annual growth
rate is close to the historical growth rate.
A major purpose of the CHECK run is to enable the user
to carefully examine the model input data, to make sure that no input errors
have occurred.
Listing 2 illustrates a run of the PROJ program, which
projects the population two five-year periods out, from the base year of 1980
to the year of 1990. From the base year
of 1980, this run projects a resident
Since the population data in the present model are
disaggregated by age and sex, the projections may be disaggregated by these
variables. Listing 2 includes
projections for all possible disaggregations. (To conserve space, later projections will
often project just a few of the possible tables and crosstabulations.) These projections may be compared in detail
to data presented in the 1990 Census of Population, General Population
Characteristics,
In general, the relative (percentage) magnitude of the
projections increases as the level of disaggregation
increases. That is, projections for a particular
category (e.g., males aged 0-5) are not as accurate in relative terms as
more-highly-aggregated projections.
Also, the magnitude of the errors increases with the distance (number of
years out) of the projection.
The principal conclusions from the present example is
that the data required for the US-population combined-race model are readily
available, and that the DESTINY projections are of a high level of accuracy in
this application.
The projection shown in Listing 2 prints the
projection only for the tenth year out.
The user may specify that the projection be printed in any future year,
and a different selection of tables and crosstabulations
may be selected for each year. For
example, the user may request that the grand total be printed for every year,
and detailed crosstabulations printed in the final
projection year.
Projection Objectives This chapter presents an example in which the DESTINY
program package is used to make projections of the US resident population by
race. The race categories used in this
example are "white" and "other than white." As in the preceding chapter, the model will
be constructed using data available prior to 1980, and used to make projections
to the year 1990. Since the model input
data are disaggregated by age, sex, and race, the projections may also be
disaggregated by any combinations of those variables.
Data Sources The present example will use the same data
sources as the preceding chapter, i.e., CP80, SA81, and VS78. The 1990 comparison data (for the projected
populations) are found in CP90 and SA92.
Migration Data As discussed in the preceding chapter, one of
the motivations for making the single-race projection of that chapter was to
obtain an estimate of the total net migration.
From the CHECK run of the preceding chapter, the value of 5,000,376 was
obtained as an estimate of the five-year net migration for the US. This number will be used in determining the
migration parameter values for the two-race model.
Input Option Parameters
In running the PARAM program, the name US802.DAT was
given to the parameter file, and the base year was identified as 1980. The file header, "US Resident Population
by Race (W/O)," was used. The seven
Input Option Parameters were as follows:
P1: Number of
races = 2
P2: Number of
regions = 1
P3: Demographic Parameter
Option = 1 (i.e., the demographic parameters are to be the same for all ten
five-year projection periods)
P4: Life Table
Option = 1 (i.e., the survival probabilities for the population will be
determined by the Infant Mortality Rate, rather than by the Expectation of Life
at Birth)
P5: External
Migration Option = 1 (i.e., a single emigration rate and/or migration number
will be specified, to be used for all projection periods)
P6: Internal
Migration Option = 0 (no regions are specified, so there is no internal
migration)
P7: Service
System Option = 0 (i.e., no service system parameters are included in the
model).
The program next requests the names of the races. The names "White" and
"Other" were entered.
The PARAM program requests entry of the demographic
data race by race. In the present
example, all of the required data are to be entered for the "white"
race, followed by all of the required data for the "other" race. To facilitate the discussion in this chapter,
however, the data shall be presented by demographic category. For example, the total fertility rate will be
presented for both races, followed by the fertility age distribution for both
races, and so on.
As in the preceding example, we shall generally use
the average value of the parameter for the five years preceding the base year,
as the value of parameters in the projection period.
Total Fertility Rates
The Total Fertility Rates for the two races included
in this example (i.e., "white" and "other than white") are
given on page 58 of SA81, in Table 84, entitled, "Total Fertility Rate and
Intrinsic Rate of Natural Increase: 1940 to 1979." For whites, the value (average of data for
1975-79) is 1.717, and for black and other races, the value is 2.334.
Fertility Age Distribution
For the preceding example, the Fertility Age
Distribution for the total US population were found on page 59 of SA81, in
Table 85, entitled, "Births and Birth Rates: 1950 to 1979." While these data were appropriate for the
combined-race model, they are not very suitable for a multi-race model, since
fertility varies significantly from race to race.
Since the DESTINY package is to be used in the present
example to make projections by race (white and other), it is desirable to specify
FAD data for the two separate races.
Better results are obtained by specifying race-specific data for the
Fertility Age Distribution. Such a
distribution is found in Table I-6 of VS78.
The following table is derived from Table I-6 of VS78:
White Other
Birth Rate Birth Rate
Age of
Mother per 1000 Women per 1000 Women
10-14 .6 4.1
15-19 43.6 99.1
20-24 106.3 145.7
25-29 111.1 117.3
30-34 57.9 66.7
35-39 17.6 27.0
40-44 3.5 6.5
45-49 .2 .4
Combining the extreme age categories (to accommodate
the DESTINY input categories), we obtain:
White Other
Birth Rate Birth Rate
Age of Mother
/1000 Women Proportion /1000 Women Proportion
15-19 44.2 .130 103.2 .221
20-24 106.3 .312 145.7 .312
25-29 111.1 .326 117.3 .251
30-34 57.9 .170 66.7 .143
35-39 17.6 .051 27.0 .058
40-44 3.7
.011 6.9
.015
Total 340.8 1.000 466.8 1.000
TFR x 1000
1704. 2334.
Note that the Total Fertility Rates (1.704 and 2.334)
for 1978 are the sums of the birth rates by age of mother, multiplied by 5 and
divided by 1,000.
It is seen from the preceding display that there is
somewhat of a difference in the Fertility Age Distribution between the races,
and it is hence preferable to use the race-specific data. (It is noted, however, that the value of the
Total Fertility Rate has a much more pronounced effect on the birth rate than
does the Fertility Age Distribution, and the difference in results introduced
by using the combined Fertility Age Distribution in place of the separate ones
would not have been very large.)
Infant Mortality Rate
Infant Mortality Rates for whites and black and other
races are found on page 73 of SA81, in Table 111, entitled, "Infant,
Material, and Neonatal Mortality Rates, and Fetal Mortality Ratios, by Race:
1940 to 1978." The rates (averages
for 1975-78) are 12.95 for whites and 22.62 for black and other races.
Base-Year Population by Age, Sex, and Race
Base-year population data by age, sex, and race are
published in CP80. The 1980 population
data published in CP80 are presented in the table which follows. The data for the white race are presented
explicitly in CP80. The data for the
other race are obtained by subtracting the white amounts from the total amounts
for all races.
White Other
Age
Category Male Female Male Female
0-4 6,482,766
6,148,431 1,877,369 1,835,841
5-9 6,684,406 6,346,611
1,853,497 1,812,620
10-14 7,407,610 7,052,673
1,907,445 1,873,191
15-19 8,631.389 8,326,152
2,120,155 2,083,971
20-24 8,680,290
8,603,095 1,979,773 2,049,399
25-29 8,004,161 7,978,484
1,699,098 1,835,929
30-34 7,298,603 7,344,080
1,376,902 1,538,372
35-39 5,830,238 5,928,994
1,029,998 1,173,778
40-44 4,849,123
4,976,012 858,427 984,677
45-49 4,638,090 4,817,869 749,421 883,003
50-54 4,918,050 5,238,845 702,424 849,665
55-59 4,852,081 5,384,727 629,071 748,175
60-64 4,172,521
4,801,456 496,786 614,948
65-69 3,841,097 4,329,974 420,986 548,787
70-74 2,551,944 3,542,234 301,172 401,392
75+ 3,187,257 5,851,527 360,145 567,618
Sex Totals 91,669,626
96,671,164 18,362,669 19,801,366
Race
Totals 188,340,790 38,164,035
Grand
Total 226,504,825
Crude Birth Rate for Base Year
From SA81, Table 85, the value for 1979 is seen to be
14.8 for whites and 22.8 for others 1979.
Crude Death Rate for Base Year
From SA81, Table 108, the value for 1979 is seen to be
8.8 for whites and 7.8 for others.
Infant Mortality Rate for the Base Year
Table 111 of SA81 provides the value of 12.0 for whites
and 21.1 for others for 1978.
Population Ten Years Prior to Base Year
From SA81 Table No. 29, page 26: "Resident
Population, by Age, Sex, and Race: 1960 to 1980," the 1970 population is seen to be 178,098,000
for whites and (by subtraction from the total 203,235,000) 25,137,000 for
others.
Average Crude Birth Rate for the Ten-Year Period Prior
to Base Year
From SA81, Table 85, the average for years 1973-79 is
seen to be 14.13 for whites and 21.77 for others.
Average Crude Death Rate for the Ten-Year Period Prior
to Base Year
From SA81, Table 108, the average for years 1973-79 is
seen to be 9.04 for whites and 8.33 for others.
Average Infant Mortality Rate for the Ten-Year Period
Prior to Base Year
From SA81, Table 111, the average for years 1972-78 is
seen to be 14.11 for whites and 24.19 for others.
External Migration
As discussed earlier, published data on immigration
refers to legal immigration, and is not suitable for use in the DESTINY
model. From the discussion of the single-race
data in the preceding chapter, an estimate of 1,000,075 was obtained for the
annual total net migration number. The
problem remains as to how to apportion this total net migration number among
the two races of the present model.
Migration numbers and rates vary considerably by race,
and so it is not satisfactory simply to allocate the total in proportion to the
US population race totals. One
indication of the relative racial composition of immigrants is provided in SA81
Table 131, entitled, "Immigrants, by Country of Birth: 1951 to
1979." The data of this table may
be used to determine an approximation of the number of white and other
immigrants.
The following data are extracted from SA81 Table 131:
Region Immigrants, 1975-79
Europe 350.4
Asia 879.2
North America 854.7
Other
10.5
Total 2,308.8
This table shows that the legal immigration from
These two immigration estimates are very approximate,
since some legal immigrants from Europe, America, Australia, and New Zealand
are surely nonwhite, some legal immigrants from other countries are surely
white, and some illegal immigrants (from any countries) are surely white. Also, emigration from the
Another limitation of the preceding estimates is that
they do not account for population changes associated with race transitioning
(which is included in the external migration parameters of the DESTINY model).
In summary, published data on migration are of limited
value for use in the DESTINY system.
Because of the unavailability of satisfactory published data on
migration by race, migration parameters will be estimated as the population
change (rate per 1,000 or amount) net of births and deaths, as was done in the
case of the all-races-combined model. As
has been discussed earlier, this estimate includes population changes
associated with race transitioning (changes in race declarations, changes in
race classification procedures, intermarriages) as well as with migration. Since the two-race model is a different
parametric specification of the population, the sum of the external migration
estimates for the two races may differ a little from the external migration
estimate calculated for the two races combined.
The formulas for estimating net external migration,
either as a rate or an amount, were given earlier. The formula for the amount is as follows:
M = (p10 - p0(1+b-d)10)(b-d)/((1+b-d)10-1)
,
where the symbols are defined as before.
Substituting b=.01413, d=.00904, p0=178,098,000,
and p10=188,340,790 for the white race yields the estimate:
M = 94,517.
Substituting b=.02177, d=.00833, p0=25,137,000,
and p10=38,164,035 for the other race yields the estimate:
M = 888,003.
The sum of these two estimates is 982,520, which
differs somewhat from the estimate of 1,000,075 for both races combined. These estimates are somewhat different from
the rough migration estimates presented above of 273,680 for whites and 726,395
for others (exclusive of race transitioning).
At this point, a decision must be made concerning whether to use these
estimates, derived from the data for the ten-year-period preceding the base
year, as the parameter values for the projection period, or whether some other
values, considered more likely to apply in the projection period, should be
used. The primary factor is whether it
is expected that the migration rates during the projection period will be
similar to those for the preceding ten-year period. Another factor to consider is whether the
amount of race transitioning for the projection period is expected to be
similar to that in the past. Since the
figure of 273,680 was considered to be an approximate lower bound for white migration
(exclusive of race transitioning), the estimate of 94,517 net external white
migration may be somewhat low for the projection period. If changes in race classification procedures
caused relatively fewer people to be classified as white in 1970 than in 1980,
and if this trend was not expected to continue, a higher figure should be used
for the projection period.
The goal of the present example is to project the
population from the base year of 1980, using data that were readily available
in 1980. To keep the example as simple
as possible, the estimated population change net of births and deaths (94,517
and 888,083) will be used for the values of the external migration parameters,
but in should be understood that other values may be used. For example, if it is believed that illegal
immigration will increase, higher values would be indicated. Or, it may be desired to construct several
alternative projections under different assumptions about external migration
levels.
This completes the data specification for the
construction of the file US802.DAT.
The output of a CHECK run of the file US802.DAT is
shown in Listing 3. For each race, the
program first prints out all of the input data.
No discrepancies are observed from the data presented above.
The estimated Total Fertility Rates for the two races
are 1.748 and 2.335, which are in close agreement with the rates specified for
the first projection period (1.717 and 2.334, respectively). The race transition parameter values as
calculated by the program are identical to the values calculated manually
above.
Listing 4 illustrates a run of the PROJ program, which
projects the population two five-year periods out, from the base year of 1980
to the year of 1990. Since the input population
data are disaggregated by age, sex, and race, the projections may be also. The total projected population for 1990 is
250,738,546, which corresponds to the actual value for 1990 of 248,710,000
(SA92, Table No. 18, "Resident Population, by Age, Race, and Hispanic
Origin: 1980 and 1990"). This is an
error of 1%. The projected population
for this example differs from the projected population for the previous (combined-race)
model since the demographic specification is different -- more detailed (two
races vs. one) -- and the projection model is nonlinear.
The projection yields values of 197,443,844 for white
and 53,294,702 for other. These
correspond to the actual 1990 values of 199,686,000 for white and (by
subtraction from the total 248,710,000) 49,024,000 for other (SA92, Table No.
18). These race-specific projections are
in error by -1.1% and 8.7%, respectively.
The white race projection is slightly low and the other race projection
is somewhat too high. Since the Total
Fertility Rate for black and other races was steadily increasing over the
period 1980-1990, the reason for the overshot is that the migration number
specified for the black and other races for the projection period was too
large. This is a not unexpected result,
in view of the fact that the value used for the external migration number
(888,003) for others exceeded the approximate upper limit (726,395) for other
migration. (Based on this result, the
migration numbers could be revised to obtain more accurate projections from a
later base year, such as 1990. It is
noted that if the values 273,680 and 726,395 are used for the migration
amounts, the 1990 projection is 199,252,780 whites and 51,620,900 others, both
of which are somewhat closer to the actual 1990 values.)
This chapter presents an example illustrating the use
of the DESTINY package to make a projection of the population of the state of
In addition to the national demographic data sources
cited earlier, the following state data sources were used:
o CPAZ80: 1980 Census of Population, Volume 1,
Characteristics of the Population, Chapter B, General Population
Characteristics, Part 4, Arizona, PC80-1-B4), issued April 1982, Bureau of the
Census, US Department of Commerce, Washington, DC.
o VSAZ80: 1980
These two publications will be referred to in the
remainder of this chapter as CPAZ80 and VSAZ80, respectively. CPAZ80 includes data on the state population
by age, sex, and race. VSAZ80 includes
data on birth and death rates.
Another source of demographic data for
For comparing DESTINY projections for 1990 to actual
1990 values, the 1990 Census of Population, General Population
Characteristics,
The example presented in this chapter is particularly
illustrative of a state-level application of the DESTINY package, since it
reveals the difficulties in obtaining accurate state-level data, and shows how
these difficulties are overcome.
As in the preceding examples, we will generally use,
if available, the average for the five years preceding the base year as the
value of parameters in the projection period.
The example presented here includes a single racial
group and region, representing the total population of the state.
In the run of the PARAM program, the name AZ801.DAT
was given to the parameter file, and the base year was stated as 1980. (In the file name, AZ stands for
P1: Number of
races = 1
P2: Number of
regions = 1
P3: Demographic
Parameter Option = 1 (i.e., the demo- graphic parameters are to be the same for
all ten five-year projection periods)
P4: Life Table
Option = 1 (i.e., the survival prob- abilities will
be determined by the Infant Mortality Rate, rather than by the Life Expectancy
at Birth)
P5: External
Migration Option = 1 (i.e., a single migration rate and/or migration number will
be specified, to be used for all projection periods)
P6: Internal
Migration Option = 0 (no regions are specified, so there is no internal
migration)
P7: Service
System Option = 0 (i.e., no service system parameters are included in the
model)
The following paragraphs describe the demographic data
input to the PARAM program.
Fertility Age Distribution; Total Fertility Rate
Total Fertility Rates are not available for
The following formula relates TFR to CBR and the
base-year population:
TFR = .005*CBR*POPT/BFAC
where
TFR = total fertility rate
CBR = crude birth rate
POPT = total population
BFAC = ' FADi*FPOPi
and
FADi = the "fertility age distribution," i.e.,
the
percentage of total lifetime births occurring to
females in the i-th five-year age cohort
FPOPi = female population in the i-th
five-year age
cohort.
All of the preceding parameters refer to the base
year.
The crude birth rate for
The total population for the base year is 2,718,215
(from CPAZ80).
Since no state-specific data are available on the
fertility age distribution, the national (all-race) data are used. These data, from SA81 Table No. 85, were presented
on the chapter dealing with the
Fertility Age Female
Age of
Mother Distribution, FADi
Population, FPOPi
15-19 .147 123,734
20-24 .312 130,297
25-29 .312 116,911
30-34 .166 102,909
35-39 .052 82,540
40-44 .011 68,279
Total 1.000
Substituting in the formula presented above, we obtain
BFAC = .147(123,734) + .312(130,297) + .312(116,911)
+.166(102,909) + .052(82,540) + .011(68,279)
=
117,443.837
and so
TFR = .005(18.4)(2,718,215)/117,443.837
= 2.129
.
Infant Mortality Rate
Data on infant mortality for
Base-Year Population by Age and Sex
Population data by age and sex are presented for the
year 1980 in CPAZ80. These data are as
follows.
Age Male Female
0-4 109,075 104,808
5-9 107,650 103,417
10-14 111,583 107,990
15-19 128,283 123,734
20-24 133,486 130,297
25-29 119,140 116,911
30-34 104,855 102,909
35-39 80,333 82,540
40-44 66,836 68,279
45-49 61,538 63,533
50-54 60,295 66,454
55-59 61,155 71,352
60-64 57,682 66,718
65-69 53,009 61,835
70-74 39,867 47,409
75+ 43,155 62,087
Total 1,337,942 1,380,273
Grand Total 2,718,215
Crude Birth Rate for Base Year
In VSAZ80, Table 2.8, the crude birth rate for
Crude Death Rate for Base Year
In VSAZ80, Table 3.3, the crude death rate for 1980 is
reported as 7.8.
Infant Mortality Rate for the Base Year
In VSAZ80, Table 3.13, the infant mortality rate for
1980 is reported as 12.4.
Population Ten Years Prior to Base Year
Numerous tables in SA81, such as Table No. 8, page 9
("Resident Population -- States 1970 to 1980") report the 1970
resident population of
Note that CPAZ80 reports (Table 20) a slightly
different figure -- 1,770,900. The
1,775,000 figure is cited more frequently, and appears in later editions of
SA. For use in the multi-race model of
the next chapter, however, the 1970 population is needed disaggregated by
race. Since these data are presented in
CPAZ80 (Table 17) but not in SA81, the CPAZ80 data (i.e., the value 1,770,900)
will be used, solely for the sake of consistency.
Average Crude Birth Rate for the Ten-Year Period Prior
to Base Year
From VSAZ80, Table 2.8, the average for years 1971-80
is seen to be 18.32.
Average Crude Death Rate for the Ten-Year Period Prior
to Base Year
From VSAZ80, Table 3.3, the average for years 1971-80
is seen to be 7.71.
Average Infant Mortality Rate for the Ten-Year Period
Prior to Base Year
From VSAZ80, Table 3.11, the average for years 1971-80
is seen to be 14.94.
External Migration
As was done before, the annual migration amount will
be estimated as the average annual population change net of births and deaths,
which is:
pt+1 = (1+b-d)pt + M
where
pt = population in year t
b = crude birth rate
d = crude death rate
M = annual (net) migration number,
and all of the parameter values represent average values
over the ten-year period prior to the base year.
Solving this equation for M in terms of p10
and p0 yields the following:
M = (p10 - p0(1+b-d)10)(b-d)/((1+b-d)10-1)
.
Substituting b=.01832, d=.00771, p0=1,770,900,
and p10=2,718,215 yields the estimate:
M = 71,507.
This completes the data specification for the
construction of the file AZ801.DAT.
The output of a CHECK run of the file AZ801.DAT is
shown in Listing 5. The printout reveals
no errors in the data entry.
The run shows that the manual computations of the
Total Fertility Rate (2.129) and the annual net migration number (71,507) were
correct.
Listing 6 illustrates a run of the PROJ program, which
projects the population two five-year periods out, from the base year of 1980
to the year of 1990. Since the input
population data are disaggregated by age and sex, the projections may be
also. The projected total population for
1990 is 3,694,625, which corresponds to the actual value for 1990 of 3,665,000
(SA92, Table No. 25, "Resident Population -- States: 1970 to
1991"). This is an error of less
than 1%.
This chapter presents an example illustrating the use
of the DESTINY package to make a multi-race, multi-region projection of the
population of the state of
In the following chapter, the DESTINY package will be
used to project social services to the elderly.
That projection will use the population model constructed in this
chapter.
The data sources used for this example are the same as
those of the preceding chapter. A minor
problem that arose in the present example in that population data were not
immediately available by county and race for 1970 (i.e., 10 years prior to the
base year). In order not to delay
preparation of the projections, the 1970 county-by-race data were
estimated. Later, the actual (1970
Census) county-by-race data were obtained.
In order to illustrate the procedure for estimating ten-year-prior
region-by-race data (for applications in which the ten-year-prior region-by-race
data are unavailable), the estimation procedure will be illustrated, and the
estimates will be compared to the actual values. The estimates will be used in this example,
rather than the actual values; in a real application, the projection would be redone
using the 1970 actual race-by-county values.
The special features illustrated in this example are
the estimation of net migration numbers by race, and the procedure for
estimating regional growth rates and migration.
The example presented here includes three racial
groups (white, American Indian, and other) and fourteen regions (the fourteen
counties of
P1: Number of
races = 3
P2: Number of
regions = 14
P3: Demographic
Parameter Option = 1 (i.e., the demo- graphic parameters are to be the same for
all ten five-year projection periods)
P4: Life Table
Option = 1 (i.e., the survival prob- abilities will
be determined by the Infant Mortality Rate, rather than by the Life Expectancy
at Birth)
P5: External
Migration Option = 1 (i.e., a single migration rate and/or migration number
will be specified, to be used for all projection periods)
P6: Internal
Migration Option = 1 (i.e., internal migra- tion among the counties will be specified)
P7: Service
System Option = 0 (i.e., no service system parameters are included in the
model)
The following paragraphs describe the demographic data
input to the PARAM program. As in the
previous chapter, the data are presented
demographic-category-by-demographic-category, rather than race-by-race (the
order requested by the PARAM program.)
Total Fertility Rates; Fertility Age Distributions
Total Fertility Rates are not available by race for
Arizona from published state vital statistics sources, and they are not
available by state in VS78. Hence, the TFRs will be estimated, using the formula
TFR = .005*CBR*POPT/BFAC
given earlier.
In order to use this formula, data are required, by race, for crude
birth rates for the base year, for the total population in the base year, for the
fertility age distribution, and for the female populations in the child-bearing
age categories.
The required population data are available from CPAZ80
(Table 17, "Race by Sex: 1900 to 1980"). The total populations for 1980 for the three
races of the model are 2,240,761 for whites, 152,498 for American Indians, and
324,956 for others.
Obtaining data on crude birth rates for 1980 is
problematic. VS78 presents crude birth
rates by state or by race, but not by race for each state. Although data on births are available by race
from VSAZ80, the racial classification used for these data do not correspond to
the racial classifications used for the population figures available from the
Census. For this reason, it is not
possible to construct rates directly from the birth-by-race data presented in
the Arizona vital statistics report (VSAZ80).
The following table presents the 1980 US Census data
on the Arizona population by race (CPAZ80, Table 17. "Race
by Sex: 1900 to 1980"), and the 1980 Arizona vital statistics data on
Arizona births by race (VSAZ80, Table 2.12).
Arizona
1980 1980 Crude
Population Race Births Birth
Race (CPAZ80)
Percent of Child (VSAZ80)
Percent Rate
White 2,240,761
82.4 White 42,308
84.6 18.9
Indian 152,498
5.6 Indian 5,061
10.1 33.2
Black 74,977
2.8 Black 2,062
4.1 27.5
Other 249,979
9.2 Asian
618 1.2
Total 2,718,215
100.0 Total 50,049
100.0
The problem is apparent: the Asian birth category of
VSAZ80 does not correspond to the Other population category of CP80. Evidently, many births that would be
classified as "other" using US Census race classification criteria
are included in other categories in the state birth counts. Birth rates estimated from the preceding data
would be seriously biased (low) for the "other" race category
(nonwhite, nonIndian) of the model.
Note that since the model will be projecting the
populations obtained from the CP80 source, it is the birth rates that must
correspond to those population categories, and not vice versa.
To overcome the comparability problem, crude birth
rates will be estimated for the white and Indian categories from the VSAZ80
data, but the US crude birth rate will be used for the other category. This approach produces 18.9 for the white
crude birth rate (VSAZ80, Table 2.12), 33.2 for the Indian crude birth rate
(also Table 2.12), and 22.8 for the other crude birth rate (SA81, Table 85).
The remaining data required by the TFR estimation
formula are the fertility age distributions and the populations of females in
the fertile age categories.
For the fertility age distributions, the
national-level data presented in VS78 will be used (no state-level FAD data are
available from VSAZ80). These data are
available for total, white, all other, and black races. The data for the "all other" race
category will be used for the Indians and other race category of the
model. These data were presented earlier
in the chapter dealing with the US two-race model, and are presented in the
following table.
Fertility Age Distribution
Age White Indian Other
15-19 .130 .221
.221
20-24 .312 .312
.312
25-29 .326 .251
.251
30-34 .170 .143
.143
35-39 .051 .058
.058
40-44 .011 .015
.015
Total 1.000 1.000 1.000
The final data required are the numbers of females in
the fertile age cohorts. These counts
are available from Table 20 of CPAZ80, and are presented in the following table
(the complete population distributions are presented later).
Female Population
Age White Indian Other
15-19 95,899 9,973
17,862
20-24 104,137 7,979
18,181
25-29 95,364 6,237
15,310
30-34 85,981 4,988
11,940
35-39 69,718 4,054
8,768
40-44 57,394 3,522
7,363
With the preceding data, the TFR estimates may now be
calculated for the three race categories.
For whites, we have:
BFAC = .130(95,899) + .312(104,137) + .326(95,364)
+.170(85,981) + .051(69,718) + .011(57,394)
=
94,850.00
and
TFR =
.005*18.9*2,240,761/94,850.00 = 2.232.
For Indians, we have:
BFAC = .221(9,973) + .312(7,979) + .251(6,237)
+ .143(4,988)
+ .058(4,054) + .015(3,522)
=
7,260.214
and
TFR = .005*33.2*152,498/7,260.214 = 3.487.
For others, we have:
BFAC = .221(17,862) + .312(18,181) + .251(15,310)
+
.143(11,940) + .058(8,768) + .015(7,363)
= 15,789.193
and
TFR = .005*22.8*324,956/15,789.193 = 2.346.
Infant Mortality Rates
Infant Mortality Rates are available from VS78 by
state, for the race categories total, white and all other (Table 2-6, "Infant
Mortality Rates by Color: United States, Each Division and State,
1974-78"). (Later editions of VS
also present data for the black race category.)
SA81 presents IMR data by state for white and black races. VSAZ80 presents birth and infant death data
for white, Indian, black, and Asian races.
Estimation of the Infant Mortality Rate (IMR) for
Arizona faces similar problems to those encountered in estimation of the Total
Fertility Rates, namely the incomparability of the Arizona vital statistics race
categories with the Census population race categories (which are used for the
model population categories). The data
presented in VSAZ80 for births (Table 2.12) and infant deaths (Table 3.12) are
as follows:
Arizona 1980
Race 1980 Race Infant Infant
of Births of Deaths Mortality
Child
(VSAZ80) Percent Child (VSAZ80) Percent
Rate
White 42,308
84.6 White 497
80.3 11.7
Indian 5,061
10.1 Indian 82
13.2 16.2
Black 2,062
4.1 Black 40
6.5 19.4
Asian 618
1.2 Asian
0 0.0
0.0
Total 50,049
100.0 Total 619
100.0 12.4
We shall use the IMRs
calculated from the VSAZ80 state data for whites (11.7) and Indians (16.2), but
use the SA81 national data for black and other races (21.1 for 1978, from Table
No. 111) for the other race category.
Base-Year Population by Age, Sex, and Race
Base-year population data by age, sex, and race are
presented in CPAZ80 (Table 20, "Age by Race and Sex: 1910 to
1980"). Unfortunately, these data
are presented for white and black (and, by subtraction, for other than white or
black), but not for white, Indian, and other than white or Indian. The Indian population is presented by age and
sex for all counties except Greenlee and
The age by sex population distribution for
White Indian Other
Category Male
Female Male Female
Male Female
0-4 79,351
76,208 9,853 9,732
19,871 18,868
5-9 80,415
76,578 9,288 9,237
17,947 17,602
10-14 85,306
82,032 9,575 9,465
16,702 16,493
15-19 99,026
95,899 9,931 9,973
19,326 17,862
20-24 106,315
104,137 7,250 7,979
19,921 18,181
25-29 96,311
95,364 5,681 6,237
17,148 15,310
30-34 87,382
85,981 4,817 4,988
12,656 11,940
35-39 68,203
69,718 3,524 4,054
8,606 8,768
40-44 56,493
57,374 3,120 3,522
7,223 7,363
45-49 52,916
54,059 2,532 3,103
6,090 6,371
50-54 53,052
58,170 2,123 2,579
5,120 5,705
55-59 55,155
64,721 1,758 2,122
4,242 4,509
60-64 53,162
61,749 1,362 1,555
3,158 3,414
65-69 49,283
57,527 1,154 1,382
2,572 2,926
70-74 37,022
44,379 928
916 1,917 2,114
75+ 39,590
57,863 1,349 1,409
2,216 2,815
Sex
Tot.1,098,982 1,141,779 74,245 78,253 164,715 160,241
Race
Totals 2,240,761 152,498 324,956
Grand
Total 2,718,215
Crude Birth Rate for Base Year
As discussed earlier, we shall use the birth rates
derived from VSAZ80 (births) and CPAZ80 (population) for the white and Indian
races, and the SA81 data for the other race category. These values are 18.9 for whites, 33.2 for
Indians, and 22.8 for others.
Crude Death Rate for Base Year
Crude death rates are available by race or by state
from SA81 and VS78, but not by state and race.
Data on deaths by race are available from VSAZ80. As was the case with the VSAZ80 data on
births, these data are not comparable with the CPAZ80 population data. The following table presents the death data
from VSAZ80 (Table 3.5).
1980 Race 1980 Crude
Population of Deaths Death
Race (CPAZ80)
Percent Child (VSAZ80)
Percent Rate
White 2,240,761
82.4 White 19,631
92.4 8.8
Indian 152,498
5.6 Indian 988
4.7 6.5
Black 74,977
2.8 Black 552
2.6 7.4
Other 249,979
9.2 Asian
55 0.3
Total 2,718,215
100.0 Total 21,226
100.0
We shall use the crude death rate from the VSAZ80 data
for whites and Indians (8.8 and 6.5 respectively), but the national-level data
from SA81 for the other race category (7.8 for 1979, Table 108).
Infant Mortality Rate for the Base Year
As discussed earlier, we shall use IMR data derived
from VSAZ80 for the white and Indian races, but national-level data presented in
SA81 for the other race category. These
rates are 11.7 for whites, 16.2 for Indians, and 21.1 for other.
In VSAZ80, Table 3.13, the infant mortality rate for
1980 is reported as 12.4.
Population Ten Years Prior to Base Year
Data for the 1970 population by race are available
from CPAZ80 (Table 17, "Race by Sex: 1900 to 1980"). These data are as follows: 1,604,948 for
whites, 95,812 for Indians, and (by subtraction from the total of 1,770,900)
70,140 for others.
Average Crude Birth Rate for the Ten-Year Period Prior
to Base Year
Data on birth rates by race for the entire ten-year
period prior to the base year are available from past editions of the Arizona
Vital Health Statistics, but these data are not readily available. For this reason, the base-year data presented
above shall be used (18.9 for whites, 33.2 for Indians, and 22.8 for others).
Average Crude Death Rate for the Ten-Year Period Prior
to Base Year
For the same reason given in the preceding paragraph
on crude birth rates, the base-year data presented above will be used (8.8 for
whites, 6.5 for Indians, and 7.8 for others).
Average Infant Mortality Rate for the Ten-Year Period
Prior to Base Year
For the same reason given above, the base-year data
presented above will be used (11.7 for whites, 16.2 for Indians, and 21.1 for
others).
Base-Year Population by Region (County)
CPAZ80 presents the population of each county, by
race. The data are presented in the
table which follows:
Population by Race (Base Year, 1980)
County White Indian
Other Total
Apache 11,902 39,024
1,182 52,108
Cochise
73,261 489 11,936
85,686
Coconino
49,235 20,904 4,869
75,008
Gila 30,147 5,083
1,850 37,080
Graham 17,085 2,740
3,037 22,862
Greenlee 9,357 229
1,820 11,406
Maricopa 1,307,455 22,788
178,809 1,509,052
Mohave 53,477 1,462
926 55,865
Navajo 32,543 32,122
2,964 67,629
Pima 442,888 14,880
73,675 531,443
Pinal
61,849 8,487 20,582
90,918
Yavapai
65,322 997 1,826
68,145
Total 2,240,761 152,498
324,956 2,718,215
External Migration
External migration will be estimated, as before, as
the change in population net of births and deaths. Using the same formula (M = (p10 -
p0(1+b-d)10)(b-d)/((1+b-d)10-1)) as before,
the estimates 44,535 for whites, 2,462 for Indians, and 22,756 for others are
obtained. These estimates are considered
"rough," since the data on fertility rates by race were approximate,
especially for the other race category.
Errors in the fertility rate will affect the migration estimate (since
this estimate is the population net of estimated births and deaths, and the
estimated births is uncertain), but these errors tend to compensate (i.e., if
the TFR for others is too low, the external migration estimate will be too
high, and vice versa).
Regional Populations Ten Years Prior to Base Year
As mentioned earlier, county-by-race data were not
immediately available (from the US Bureau of the Census) for the year 1970, and
so these data were estimated. Later, the
actual 1970 data were received. The
following paragraphs illustrate a procedure for estimating region-by-race data
for a ten-year-earlier year, using base-year region-by-race data.
The data that were initially available for 1970 were
the population totals for the three races and the population totals for the 14
counties (i.e., the "marginal" totals are available for race and
county). For 1980, the data were
available for county-by-race. These data
may be used to compute estimates of the proportion of population in each
race-by-county category. What is desired
is to determine an allocation of the 1970 population over the various
race-by-county categories that matches the marginal race and county totals, for
which the race-by-county proportions are "close" to the 1980 values.
The problem of determining a set of race-by-county
category counts that matches the specified marginal totals and is close to the
specified cell proportions is called "statistical adjustment of
data." The recommended procedure
for solving this problem is to determine the adjustments by the method of
least-squares, using a procedure known as "Deming-Stefan
raking." To avoid the complexity of
this (iterative) method, we shall use a simpler procedure.
The procedure we shall use involves two steps. First, we shall apportion the total 1970
population for each race to the counties in proportion to the 1980 county
populations for the race. The problem
that arises is that the county populations (summed over all races) obtained in
this way may not match the known 1970 totals.
To address this problem, the population values for the white race
(usually the largest in every county) will be adjusted (in each county) to
force the county total to match the known 1970 county total.
The result of applying the first step produces the
following table:
Population by Race (Estimated, 1970, Unadjusted)
Unadjusted 1970
County White Indian
Other Total Total
Apache 8,525 24,518
255 33,298 32,298
Cochise
52,473 307 2,576
55,356 61,910
Coconino
35,265 13,134 1,051
49,450 48,326
Gila 21,593 3,194
399 25,186 29,255
Graham 12,237 1,721
656 14,614 16,578
Greenlee 6,702 144
393 7,239 10,330
Maricopa 936,466
14,317 38,595 989,378
967,522
Mohave 38,303 919
200 39,422 25,857
Navajo 23,309 20,182
640 44,131 47,715
Pima 317,219 9,349
15,902 342,470 351,667
Pinal
44,299 5,332 4,443
54,074 67,916
Yavapai
46,787 626 394
47,807 36,733
Total 1,604,948 95,812
70,140
1,770,900 1,770,900
The result of adjusting the white county amounts so
that the three races sum to the correct county totals (by adding the 1970 total
less the unadjusted total to each white amount) is as follows:
Population by Race (Estimated, 1970)
1970
County White Indian
Other Total
Apache 7,525 24,518
255 32,298
Cochise
59,027 307 2,576
61,910
Coconino
34,141 13,134 1,051
48,326
Gila 25,662 3,194
399 29,255
Graham 14,201 1,721
656 16,578
Greenlee 9,793 144
393 10,330
Maricopa 914,610
14,317 38,595 967,522
Mohave 24,738 919
200 25,857
Navajo 26,893 20,182
640 47,715
Pima 326,416 9,349
15,902 351,667
Pinal
58,141 5,332 4,443
67,916
Yavapai
35,713 626 394
36,733
Total 1,604,948 95,812
70,140
1,770,900
The entries of this table are entered into to program
as the regional populations ten years prior to the base year.
The following table shows the actual 1970
region-by-race values, for comparison to the estimated values. (The source of the data is 1970 Census of
Population, Volume 1, Characteristics of the Population, Part 4:
Population by Race (Actual 1970)
1970
County White Indian
Other Total
Apache 7,734 23,994
570 32,298
Cochise
59,250 152 2,508
61,910
Coconino
34,512 11,996 1,818
48,326
Gila 24,409 4,591
255 29,255
Graham 14,124 1,682
772 16,578
Greenlee 10,099 124
107 10,330
Maricopa 914,464
11,159 41,899 967,522
Mohave 24,850 869
138 25,857
Navajo 23,425 23,023
1,267 47,715
Pima 329,278 8,837
13,552 351,667
Pinal
57,516 6,405 3,995
67,916
Yavapai
35,754 686 293
36,733
Total 1,604,948 95,812
70,140
1,770,900
In general, the estimated values are close to the actual
values. Large relative errors occur for
some of the counties having very small numbers of Indian and other races. Except for these instances, using the
estimated values instead of the actual values will have a negligible impact on
the projection results.
Internal Migration
As discussed earlier, the parameters used to determine
internal migration are the amount (or rate) of population change net of births,
deaths, and net external migration allocated proportional to region (county)
population size.
The formulas for estimating the internal migration
parameter values are similar to those used for estimating external migration
parameters.
The formulas for the internal migration amount (N) and
the internal migration rate (n) are:
N = (p10 - p0(1+b-d+m)10)(b-d+m)/((1+b-d+m)10-1) - M
and
n = ((p10-MC)/p0).1
-1 - b + d - m,
where
C = ' (1+b-d+m+r)i ,
the sum is from 1 to 9, and the other symbols are as
previously defined. In this case,
however, p10 refers to a county population of a particular race in
the base year, and p0 refers to the county population of a
particular race ten years previous.
Also, the value of M for each county is the total external migration for
the race times the proportion of the race in that county, where the external
migration is estimated (as above) as the population change net of births and
deaths.
The formula for the amount is a closed-form
expression, whereas the formula for the rate is not (i.e., n occurs on both
sides of the equation and it is not possible to obtain a closed-form expression
for n). The CHECK program evaluates both
of these expressions (using an iterative method for the rate), and so it is not
necessary to perform the computations by hand.
As an approximation for the rate, the amount divided
by the population, times 1,000, may be used.
The following table presents the values of the
internal migration amounts and rates (per 1,000) for the three races, as
determined by the preceding formula for N and n. As discussed earlier, the amount will be used
(entered to the PARAM program) if the estimate is positive (or zero), and the
rate will be used otherwise.
Internal Migration Amounts and Rates
White Indian Other
County Amount
Rate Amount Rate
Amount Rate
Apache 106
11.257 0 .001
0 .021
Cochise
-692 -10.599 0
.070 0 .005
Coconino
119 2.290 0
-.003 0 -.002
Gila -430
-15.539 0 -.013
0 .033
Graham -207
-13.399 0 .027
0 -.031
Greenlee -327 -34.043
0 -.079 0
-.018
Maricopa 2,309 2.130
0 .002 0
.000
Mohave 1,433
39.480 0 -.045
0 -.027
Navajo -379
-12.877 0 -.001
0 -.016
Pima -972
-2.576 0 -.001
0 .001
Pinal
-1,462 -24.442 0
.004 0 -.005
Yavapai
1,170 24.387 0
.059 0 .014
Total 0 0 0
The internal migration amounts for Indians and others
are zeros for all counties because the populations for 1970 for those races
were estimated for each county as proportional to the 1980 populations.
Some of the internal migration rates are so large that
it is difficult to imagine that they would continue for very long. The value 39.480 for the white race in
This completes the data specification for the
construction of the file AZ803.DAT.
The output of a CHECK run of the file AZ803C.DAT is
shown in Listing 7. The printout reveals
no errors in the data entry.
The run shows that the manual computations of the
Total Fertility Rates (2.232, 3.487, and 2.346) were correct.
Listing 8 illustrates a run of the PROJ program, which
projects the population two five-year periods out, from the base year of 1980
to the year of 1990. Since the input population
data are disaggregated by age, sex, race, and region, the projections may be
also. The total projected population for
1990 is 3,735,219, which corresponds to the actual value for 1990 of 3,665,000
(SA92, Table No. 25, "Resident Population -- States: 1970 to
1991"). This is an error of 1.9%.
Note that the 1990 total-population projection of this
model differs slightly from the 1990 total-population projection of the
single-race model of the preceding chapter (3,694,625). It is not quite as accurate, probably a
result of the difficulty of estimating net migration by race.
The projections for 1990 by race are 2,886,323 for
whites, 228,240 for Indians, and 620,656 for others. These may be compared to the actual 1990
figures available from the 1990 Census (1990 Census of Population, General
Population Characteristics, United States, 1990 CP-1-1, issued November,
1992, US Department of Commerce, Bureau of the Census, Washington, DC
(henceforth referred to as CP90), Table 262, "Age and Sex by Race and
Hispanic Origin: 1990"): 3,665,228 total, 2,963,186 for whites, 203,527
for Indians, and (by subtraction) 498,515 for others. The errors in these race-by-race projections
are -2.6% for whites, 12.1% for Indians, and 24.5% for others. These results are displayed in the following
table.
1990 Projected 1990 Actual Percentage
Race Population Population Error
White 2,886,323 2,963,186 -2.6
Indian 228,240 203,527 12.1
Other 620,656 498,515 24.5
Total 3,735,219 3,665,228 1.9
The projection for the other race is poor. The reason for this is that the explosive
growth in this racial group from 1970 to 1980 (70,140 to 324,956, or an average
annual rate of 16.6% dropped dramatically for the 1980-1990 decade (from
324,956 to 498,515, or an average annual rate of only 4.4%). It is not known whether this dramatic drop in
the growth rate of the other race category is the result of substantial changes
in race classification procedures, racial mixing, or a real drop in the number
of other-race persons migrating to Arizona.
The projections for 1990 by county may be compared to
the 1990 actual values, available from the County and City Data Book, 1994,
US Department of Commerce, Bureau of the Census, Washington, DC. The following table compares the 1990 county
projections and the 1990 actual values.
1990 Projected 1990 Actual Percentage
County Population Population Error
Apache 72,497 61,591 17.7
Cochise
97,683 97,624 .1
Coconino
97,171 96,591 .6
Gila 40,759
40,216 1.4
Graham 26,383 26,554 -.6
Greenlee 11,039 8,008 37.8
La
Paz * 13,884 *
Maricopa 1,893,992 2,122,101 -10.7
Mohave 83,827 93,497 -10.3
Navajo 84,127 77,658 8.3
Pima 649,633 666,880 -2.6
Pinal
101,590 116,379 -12.7
Santa
Cruz 24,075
29,676 -18.9
Yavapai
95,609 107,714 -11.2
Yuma 108,068 106,895 -10.5*
Total 3,735,219 3,665,228 1.9
No projection is available for La Paz County, since
that county was created in 1983, and was not included in the model. Since that county was created from Yuma
County, the sum of the 1990 actual populations for La Paz and Yuma Counties
(120,779) should be compared to the projection for Yuma County (108,068). The error in this projection is -10.5%. The largest projection error is for Greenlee
County, for which the population decreased from 11,406 to 8,008 between
1980 and 1990.
The average absolute projection error for the county
projections is 10.4%. For 10-year-out
projections for highly disaggregated local areas in a state in which the
population is growing rapidly because of migration, errors of this magnitude
are considered very reasonable. The
magnitude of the errors for nearer-term projections would be less.
The following table shows the 1990 projections by race
and county and compares them to the 1990 actual values. The actual values are from CCDB94, with the
"other" race obtained by subtracting the white and Indian amounts
from the county totals.
1990 Population by Race and County
White Indian Other
County Projected Actual Projected Actual
Projected Actual
Apache 15,397
12,456 55,256 47,803
1,844 1,332
Cochise
78,373 79,724 692
790 18,618 17,110
Coconino
59,977 61,836 29,599
28,233 7,595 6,522
Gila 30,676 30,776
7,197 5,238 2,886
4,202
Graham 17,766
20,603 3,880 3,951
4,737 2,000
Greenlee 7,876
6,835 324 183
2,839 990
La Paz *
10,335 * 2,402
* 1,107
Maricopa
1,582,814 1,799,420
32,267 38,017 278,911
284,664
Mohave 80,313
88,834 2,070 2,145
1,444 2,518
Navajo 34,020
34,205 45,483 40,417
4,623 3,036
Pima 513,643
524,976 21,069 20,330 114,920 121,574
Pinal
57,469 87,219 12,017
10,785 32,104 18,375
Sta Cruz
17,931 22,159 81
64 6,063 7,453
Yavapai 91,349
103,106 1,412 1,740
2,848 2,868
Yuma 76,044* 80,702* 4,582*
1,429* 27,442* 24,764*
Total 2,886,323 2,963,186 228,240 203,527 620,656
498,515
Even though the level of disaggregation
is quite high and the number of years out is far (10 years), the projections
are reasonably close to the actual values in magnitude in most cases. Substantial relative errors may occur for
counties having small populations of the other race category. The relative projection error may be reduced
by combining (adding together) counties having small populations of the other
races.
Recall that the actual totals for La
Paz and Yuma Counties is to be compared to the projected for Yuma
County.
This chapter presents an example illustrating the use
of the DESTINY package to project the Hispanic population of the state of
Arizona. The model is a
"two-race" one, in which the two "race" categories are Hispanic
and other (non-Hispanic). The model
includes representation of the 14 Arizona counties of 1980.
Any racial, ethnic, or other classification of a
population may be represented as a "race" in the DESTINY model. The classification Hispanic/other is not a
racial one, the model treats this classification in the same fashion as it does
actual races. To maintain parallelism of
the presentation of this chapter with that of previous chapters, the discussion
of this chapter will refer to the two categories of the Hispanic/other
classification as "races" of the model, even though they are not
races in the ethnic sense.
There is the likelihood of some confusion in the
descriptors used for the racial categories of this model, when references are
being made to some of the other multi-race models. The problem is that the term
"other" becomes ambiguous when several different multi-race models
are under discussion. It may refer to
"other than white," or "other than white and Indian," or
"other than Hispanic." To
avoid confusion, and yet avoid using such awkward descriptors (particularly in
table titles), we shall make occasional use of terms such as
"nonwhite" and "nonHispanic,"
despite the current "political incorrectness" of ethnic category
descriptors having the prefix "non."
One needed data element needed for the present example
that is not available from the referenced sources is the 1970 Arizona
population by Hispanic status (for the whole state and by county). The 1970 county-by-Hispanic-status data will
hence be estimated. Hispanic-status data
are available for 1980 and later years, so this is no longer a problem in using
the program to make forecasts from a base year of 1990 or later.
The approach used earlier to estimate 1970 populations
for whites, Indians, and others does not work here, since the 1970 population
totals are not available for Hispanics and nonHispanics. Hence, it is not possible to apportion a
known 1970 race population total over the counties in the same proportions as
observed for 1980. Instead, it will be
assumed that the relative proportion of the races (Hispanic and nonHispanic) in each county was the same in 1970 as in
1980, and apportion the 1970 total county population (which is known) between
the two races accordingly. This
procedure provides estimates of the population of each county by race and, by
summing, estimates of the total population of each of the two races.
The example presented here includes two ethnic groups
(Hispanic and other) and fourteen regions (the fourteen counties of Arizona in
1980). (As noted earlier, in 1983, Yuma
County was split to form the two counties of Yuma and La Paz. The Yuma County of the example presented here
refers to the union of the present Yuma and La Paz Counties.) In the run of the PARAM program, the name
AZ80HC.DAT was given to the parameter file, and the base year was stated as
1980. (In the file name, AZ stands for Arizona,
80 stands for 1980, H stands for Hispanic, and C stands for county.) The seven Input Option Parameters were as
follows:
P1: Number of
races = 2
P2: Number of
regions = 14
P3: Demographic
Parameter Option = 1 (i.e., the demo- graphic parameters are to be the same for
all ten five-year projection periods)
P4: Life Table
Option = 1 (i.e., the survival prob- abilities will
be determined by the Infant Mortality Rate, rather than by the Life Expectancy
at Birth)
P5: External
Migration Option = 1 (i.e., a single migration rate and/or migration number
will be specified, to be used for all projection periods
P6: Internal
Migration Option = 1 (i.e., internal migra- tion among the counties will be specified)
P7: Service
System Option = 0 (i.e., no service system parameters are included in the
model)
The following paragraphs describe the demographic data
input to the PARAM program. As in the
previous chapter, the data are presented
demographic-category-by-demographic-category, rather than race-by-race (the
order requested by the PARAM program.)
Total Fertility Rates; Fertility Age Distributions
Total Fertility Rates are not available by Hispanic
status for Arizona from published state vital statistics sources, and they are
not available by state in VS78. Hence,
the TFRs will be estimated, using the formula
TFR = .005*CBR*POPT/BFAC
given earlier.
In order to use this formula, data are required, by Hispanic status, for
crude birth rates for the base year, for the total population in the base year,
for the fertility age distribution, and for the female populations in the
child-bearing age categories.
The required population data are available from CPAZ80
(Table 16, "Total Persons and Spanish Origin Persons by Type of Spanish
Origin and Race: 1980"). The total
populations for 1980 for the two races of the model are 440,701 for Hispanics
and 2,277,514 for others.
The crude birth rates for 1980 are estimated from data
on births presented in VSAZ80. For 1980,
Table 2.12 reports 13,082 Hispanic births out of a total of 50,049 births,
implying (by subtraction) that there are 36,967 in the other (nonHispanic) category.
Dividing these figures by the respective populations produces the crude
birth rate of 29.7 for Hispanics and 16.2 for others (nonHispanics).
The remaining data required by the TFR estimation
formula are the fertility age distributions and the populations of females in
the fertile age categories.
For the fertility age distributions, the
national-level data presented in VS78 will be used (no state-level FAD data are
available from VSAZ80). These data are
available for total, white, all other, and black races. The total fertility rates for these four
categories are 1.799, 1.708, 2.312, and 2.284, respectively. Data are not available by Hispanic
status. Hispanic persons may be of any
race. Since the Hispanic group has a
very high birth rate, its fertility rate is high. Groups having high fertility rates typically
have a FAD that has larger probabilities in the lower-age categories, such as
the "all other" and "black" FADs. This suggests using either the "all
other" or "black" FADs for the
Hispanic category.
With respect to the "other" (nonHispanic) category of the model, it is observed that it
is heavily white, since the combined size of the other racial groups (Indians,
blacks, etc.) is small. This suggests
using the "white" FAD for the nonHispanic
category.
In view of the preceding considerations, we shall use
the "all other" FAD for the Hispanic category and the
"white" FAD for the nonHispanic category of
the model.
The FAD data for these categories were presented
earlier, in the chapter on the US two-race model, and are repeated here.
Fertility Age
Distribution
Age of
Mother Hispanic Other(NonHispanic)
15-19 .221 .147
20-24 .312 .312
25-29 .251 .312
30-34 .143 .166
35-39 .058 .052
40-44 .015 .011
Total 1.000 1.000
The final data required are the numbers of females in
the fertile age cohorts. These counts
are available from Table 45 of CPAZ80 ("Age by Race, Spanish Origin, and
Sex for Counties: 1980"). The data
in this table are presented county by county, and must be totalled
to obtain the total populations for all counties. The complete population distributions are
presented later.
Female Population
Age Hispanic Other (NonHispanic)
15-19
24,824 98,910
20-24 22,734 107,563
25-29 19,195 97,716
30-34 15,780 87,129
35-39 12,241 70,299
40-44 10,217 58,062
With the preceding data, the TFR estimates may now be
calculated for the two race categories.
For Hispanics, we have:
BFAC = .221(24,824) + .312(22,734) + .251(19,195)
+
.143(15,780) + .058(12,241) + .015(10,217)
=
20,516.83
and
TFR = .005*29.7*440,701/20,516.83
= 3.190.
For others (nonHispanics),
we have:
BFAC = .147(98,910) + .312(107,563) + .312(97,716)
+
.166(87,129) + .052(70,299) + .011(58,062)
=
97,344.462
and
TFR = .005*16.2*2,277,514/97,344.462 = 1.895.
Infant Mortality Rates
Infant Mortality Rates are available from VS78 by
state, but not by Hispanic status.
VSAZ80 presents data on births by Hispanic status, but not infant deaths
by Hispanic status. Infant deaths are
reported for the categories all races, white, and nonwhite. Rather than make somewhat tenuous assumptions
about which of these categories might approximate the IMR experience of
Hispanics, we shall simply use the overall IMR for both Hispanics and nonHispanics. For
1980 the birth data are 50,049 total births, and the infant death data are
619. Dividing these numbers yields the
rate 12.4.
Base-Year Population by Age, Sex, and Hispanic Status
Base-year population data by age, sex, and Hispanic
status are presented in CPAZ80 (Table 45, "Age by Race, Spanish Origin,
and Sex for Counties: 1980").
Summing over the counties produces the following population distribution
by age, sex, and Hispanic status for the state.
Hispanic Other(NonHispanic)
Category Male
Female Male Female
0-4 27,940
26,823 81,135 77,985
5-9 25,652
25,079 81,998 78,338
10-14 24,234
23,538 87,349 84,452
15-19 26,081
24,824 102,202 98,910
20-24 23,080
22,734 110,406 107,563
25-29 20,171
19,195 98,969 97,716
30-34 15,889
15,780 88,966 87,129
35-39 11,668
12,241 68,665 70,299
40-44 9,644
10,217 57,192 58,062
45-49 8,380
9,015 53,158 54,518
50-54 7,608
8,290 52,687 58,164
55-59 6,317
6,759 54,838 64,593
60-64 4,672
5,073 53,010 61,645
65-69 3,525
3,986 49,484 57,849
70-74 2,545
2,938 37,322 44,471
75+ 2,840 3,963
40,315 58,124
Sex Tot. 220,246
220,445 1,117,696 1,159,818
Race
Totals 440,701 2,277,514
Grand
Total 2,718,215
Crude Birth Rate for Base Year
As discussed earlier, we shall use the birth data
available in VSAZ80 to calculate the crude birth rate of 29.7 for Hispanics and
16.2 for others (nonHispanics).
Crude Death Rate for Base Year
Data on deaths by Hispanic status are not available
from any of the referenced sources.
VSAZ80 reports the death rate for all persons in Arizona (based on a
total of 21,226 deaths) as 7.8. This
number will be used for both Hispanics and nonHispanics.
Infant Mortality Rate for the Base Year
As discussed earlier, we shall use the single IMR,
12.4, for both Hispanics and nonHispanics.
Population Ten Years Prior to Base Year
As discussed in the introduction to this chapter, data
are not available on Hispanic status of the Arizona population for the year
1970, and the hypothetical numbers 282,293 and 1,488,607 will be used in place
of the actual number of Hispanics and nonHispanics. This number does not affect the projections,
but it does affect the population growth estimates produced by the CHECK
program.
Average Crude Birth Rate for the Ten-Year Period Prior
to Base Year
In lieu of better estimates, the base-year crude birth
rate estimates of 29.7 and 16.2 will be used.
Average Crude Death Rate for the Ten-Year Period Prior
to Base Year
The base-year crude death rate of 7.8 will be used for
both Hispanic and nonHispanic statuses, in lieu of
better estimates.
Average Infant Mortality Rate for the Ten-Year Period
Prior to Base Year
For the same reason given above, the base-year data
presented above will be used (12.4 for both Hispanics and nonHispanics).
External Migration
As before, external migration will be estimated as the
population change net of births and deaths.
Using this procedure, the estimates of net external migration are 8,159
per year for Hispanics and 63,450 for nonHispanics. (Note that the total of these estimates,
71,609, is close to the net external migration estimate of 71,507 obtained for
the combined-race model.
Base-Year Population by Region (County)
CPAZ80 presents the Hispanic population of each
county, by Hispanic status (Table 16, "Total Persons and Spanish Origin
Persons by Type of Spanish Origin and Race: 1980"). The data are presented in the table which
follows:
Population by Hispanic Status (1980)
County Hispanic Other (NonHispanic) Total
Apache 1,983 50,125 52,108
Cochise 22,846 62,840 85,686
Coconino
7,315 67,693 75,008
Gila 7,723 29,357 37,080
Graham 5,457 17,405 22,862
Greenlee 5,446 5,960 11,406
Maricopa 199,003 1,310,049 1,509,052
Mohave 2,148 53,717 55,865
Navajo 4,538 63,091 67,629
Pima 111,418 420,025
531,443
Pinal
26,752 64,166 90,918
Santa
Cruz 15,229 5,230 20,459
Yavapai
4,205 63,940 68,145
Yuma 26,638 63,916 90,554
Total 440,701 2,277,514 2,718,215
Regional Populations Ten Years Prior to Base Year
As mentioned earlier, county-by-race data were not
collected until the 1980 Census, and so such data are not available for the year
(1970) ten years prior to the base year of this example. We shall estimate the 1970 county populations
by race by apportioning the 1970 population of each county between the races in
the same proportion as existed in 1980.
The result of this procedure is shown in the following table. The populations under the column labeled
"Total" are known (not estimated).
The other two populations in each row are estimated. This is a rough estimate, since the fertility
rates for Hispanics and nonHispanics are believed to
be substantially different. A more
elaborate procedure could be used to obtain better estimates, but these
estimates are quite adequate for illustration purposes.
Population by Hispanic Status (Estimated, 1970)
County Hispanic Other (NonHispanic) Total
Apache 1,229 31,069 32,298
Cochise
16,507 45,403 61,910
Coconino
4,713 43,613 48,326
Gila 6,093 23,162 29,255
Graham 3,957 12,621 16,578
Greenlee 4,932 5,398 10,330
Maricopa 127,590 839,932 967,522
Mohave 994 24,863 25,857
Navajo 3,202 44,513 47,715
Pima 73,728 277,939 351,667
Pinal
19,984 47,932 67,916
Santa
Cruz 10,396 3,570 13,966
Yavapai
2,267 34,466 36,733
Yuma 17,893 42,934 60,827
Total 293,485 1,477,415 1,770,900
Internal Migration
As before, internal migration is estimated as the
population change net of births and deaths and proportional allocation of
external migration to the regions. The
following table presents the results of this estimation (using the formulas for
the rate, n, and the amount, N). The
rate is per 1,000 people. As noted
before, there is no need to compute any of the internal migration parameter
estimates (table entries) by hand, since the CHECK program computes them and
displays them.
Internal Migration Amounts and Rates
Hispanic NonHispanic
County Amount
Rate Amount Rate
Apache 10.
6.697 151. 3.852
Cochise
-145. -7.581 -486.
-9.138
Coconino
18. 3.079 31.
.579
Gila -107.
-15.731 -431. -16.613
Graham -36.
-7.913 -139. -9.445
Greenlee -147. -28.458
-160. -28.348
Maricopa 555. 3.535
1035. .991
Mohave 49.
34.036 1045. 28.402
Navajo -20.
-5.378 -375. -7.120
Pima 53. .593
-573. -1.684
Pinal
-244. -10.672 -660.
-11.968
Santa Cruz -29. -2.304
-19. -4.317
Yavapai 60. 19.723
734. 15.632
Total 0 0
As usual, the rate is used if it is negative and the
amount is used if it is positive.
This completes the data specification for the
construction of the file AZ80HC.DAT.
The output of a CHECK run of the file AZ80HC.DAT is
shown in Listing 9. The printout reveals
no errors in the data entry.
The run shows that the manual computations of the
Total Fertility Rates (3.190 and 1.895) were correct.
Listing 10 illustrates a run of the PROJ program,
which projects the population two five-year periods out, from the base year of
1980 to the year of 1990. Since the
input population data are disaggregated by age, sex, race, and region, the
projections may be also. The total
projected population for 1990 is 3,702,132, which corresponds to the actual
value for 1990 of 3,665,000 (SA92, Table No. 25, "Resident Population --
States: 1970 to 1991"). This is an
error of approximately 1%.
Note that the 1990 total-population projection of this
model differs slightly from the 1990 total-population projection of the
single-race model for
The projections for 1990 by race are 647,662 for
Hispanics and 3,054,470 for nonHispanics. These may be compared to the actual 1990
figures available from the 1990 Census (1990 Census of Population, General
Population Characteristics, United States, 1990 CP-1-1, issued November,
1992, US Department of Commerce, Bureau of the Census, Washington, DC
(henceforth referred to as CP90), Table 262, "Age and Sex by Race and
Hispanic Origin: 1990"): 3,665,228 total, 688,388 for Hispanics, and (by
subtraction) 2,976,840 for nonHispanics. The errors in these race-by-race projections
are -5.9% for Hispanics and 2.6% for others.
These results are displayed in the following table.
1990 Projected 1990 Actual Percentage
Ethnic
Group Population Population Error
Hispanic 647,662 688,388 -5.9
Other (nonHisp.)
3,054,470 2,976,840 2.6
Total 3,702,132 3,665,228 1.0
The projections for 1990 by county and Hispanic status
may be compared to the 1990 actual values, available from the County and
City Data Book, 1994, US Department of Commerce, Bureau of the Census,
Washington, DC. The following table compares
the 1990 county projections and the 1990 actual values.
Hispanic
Population
1990 Projected 1990 Actual Percentage
County Population Population Error
Apache 2,867 2,599 10.3
Cochise
29,228 28,379 3.0
Coconino
10,332 9,696 6.6
Gila 9,098 7,486 21.5
Graham 6,958 6,682 4.1
Greenlee 5,633 3,456 63.0
Maricopa 281,931 345,498 -18.4
Mohave 3,602 4,919 -26.8
Navajo 5,936 5,652 5.0
Pima 153,500 163,262 -6.0
Pinal
33,174 34,062 -2.6
Yavapai
6,584 6,899 -4.6
Total 647,662 668,338 -5.9
No projection is available for
The mean absolute deviation of the relative projection
errors for the race-by-county Hispanic population projections is 14.6%. As might be expected, the relative
(percentage) error is largest for counties having small Hispanic populations. For ten-year-out regional projections of a
small minority in a state whose population is changing very rapidly, the
accuracy of the projections is considered, overall, quite good.
NonHispanic
Population
1990 Projected 1990 Actual Percentage
County Population Population Error
Apache 62,147 58,992 5.3
Cochise
69,032 69,245 -.3
Coconino
81,880 86,895 -5.8
Gila 29,898 32,730 -8.7
Graham 19,061 19,872 -4.1
Greenlee 5,383 4,552 18.3
Maricopa 1,589,762 1,776,603 -10.5
Mohave 77,062 88,578 -13.0
Navajo 70,732 72,006 -1.8
Pima 497,322 503,618 -1.3
Pinal
68,501 82,317 -16.8
Yavapai
85,688 100,815 -15.0
Total 3,054,470 2,976,890 2.6
No projection is available for
The mean absolute deviation of the projection errors
for the ten-year-out race-by-county projections for the nonHispanic
population is 7.3%. This level of
accuracy for regional projections of a particular ethnic group is quite good.
Both the Hispanic and nonHispanic
results show that the relative error of a ten-year-out projection can be
substantial for counties having small respective populations. As mentioned earlier, the relative projection
error may be reduced by combining counties having very small populations (of a
particular race).
This chapter illustrates a typical use of the DESTINY
program -- the estimation of a target population, based on available incidence
or prevalence data. This example
illustrates the application of the technique of "synthetic
estimation," by which national incidence/prevalence rates by demographic
category are used to construct state estimates.
This procedure assumes, of course, that the national rates do in fact
apply to the state.
In order to use the DESTINY system, it is necessary to
enter data on the incidences or prevalences of
conditions of interest. In some cases,
such data are available directly from published sources, but in many cases the
available data are not in the exact form required for input to the program, and
some additional processing or assumptions are required to obtain data in the
exact form needed. The examples
presented in this and the following chapters will illustrate in detail the way
in which the required data may be obtained from available data.
Service-system data may be specified to the program in
varying levels of detail, ranging from values (means or proportions) for the
entire population to rates by age, sex, race, and region. The level of detail used for the data entry
should match, whenever possible, the level of detail desired for the
output. For example, if it is desired to
make projections of the number of persons with a work disability by age, then
the prevalence of persons with a work disability should, if possible, be specified
by age. If it is desired to make projections
by race, then the prevalences should be specified by
race (unless it can be shown or safely assumed that the prevalences
do not vary much by race).
The example of this and the next several chapters will
illustrate the use of the DESTINY system to project the number of persons with
having various conditions for the state of Arizona, and the services,
resources, and costs associated with these "target" populations. These examples will use the three-race,
14-region population data base (parameter file) that was presented
earlier. The PARAM program is used to
derive the data base for these examples from the AZ803C.DAT data base presented
earlier. When the program requests
ENTER NAME OF OLD PARAMETER FILE (12X):
the user enters AZ803C.DAT, and when the program
requests
ENTER NAME OF NEW PARAMETER FILE (12X):
the user enters, for example, AZ803CD.DAT
("D" for "work disabled").
From this point on, the program prints out sections of
the AZ803C.DAT parameter file, requesting the user to accept the original
values or to modify them.
The first change to the data base is to change the
value of the Input Option parameter P7 to reflect the fact that a "service
system" will be included in the model:
P7: Service
System Option = 1 (i.e., service system parameters are included in the model)
The program prints out all of the input option
parameters, and requests:
ENTER 1 TO CHANGE PRECEDING PARAMETERS, 0 TO LEAVE AS
IS:
The user enters a 1 and reenters the values as before,
except for the Service System Option parameter, for which the value is changed
from a 0 to a 1. From this point on, the
user accepts all of the original file parameters, since the demographic
specification is exactly as before. When
the demographic-parameter section of the program is finished, the program
requests entry of the target-population and/or service-system parameters.
As discussed earlier, service system data include data
on target populations, service populations, services, resources, and
costs. The example of the present
chapter will include just target population data, but the examples of later
chapters will include more elaborate service-system specifications.
In some cases, service-system data may be available
for the same political unit of the population data base (in these examples,
The present example will estimate the numbers of
persons with work disabilities. There
are two target populations: persons with severe work disabilities and persons
with partial work disabilities. The
target population and service-system parameter values to be specified to the
PARAM program are as follows:
No. of target populations = 2 (i.e,
severely work-disabled and partially work-disabled)
Service Population Option = 0 (i.e., no service-system
data will be included in the model)
Names of target populations: WRKDISSV, WRKDISPT .
Information about work disabilities is presented in
SA81, Table 555, "Persons with Work Disability, by Selected
Characteristics: 1978." A portion
of this table is presented below. In
this example, it is assumed that the national data on the prevalence of work
disabilities may be used as a proxy for the state prevalences.
Persons with Work Disability (percent)
Characteristic Severely Partially
18-24 years
old 2.2 4.0
25-34 years
old 3.0 7.2
35-44 years
old 6.5 8.5
45-54 years
old 11.3 12.8
55-64 years
old 24.9 12.1
There are two problems with the available data, from
the point of view of data entry to the DESTINY system. First, the data are relative to the civilian noninstitutionalized population and members of Armed Forces
living off post or with their families on post.
The population included in the three-race, 14-region AZ803C.DAT data
base are resident population. The total
resident population of the US in 1980 was 226,505,000, and the total civilian noninstitutionalized population was 220,208,000
(227,020,000 total population (Table 30 SA81) less 2,051,000 military
population (Table 602 SA81) less 5,786,000 population in institutions and other
group quarters (1970 est., Table 77 SA81) + 1,025,000 in military barracks
already subtracted (Table 77 SA81) = = .
Since the population data in the data base are resident population, all
incidences and prevalences must be expressed relative
to that population. The percentages
presented in the above table will be converted to percentages of the resident
population by multiplying by the factor 220,208,000/226,505,000 = .972199. Multiplying by this factor produces the
following table. (Had data on the
civilian noninsitutionalized population of Arizona in
1980 been available, this adjustment factor would have been obtained from the
state, rather than the national, populations.)
Persons with Work Disability
(percent)
Characteristic Severely Partially
18-24 years
old 2.1 3.9
25-34 years
old 2.9 7.0
35-44 years
old 6.3 8.3
45-54 years
old 11.0 12.4
55-64 years
old 24.2 11.8
The second problem with the available data is that
they do not match the five-year age categories of the DESTINY program (0-4,
5-9, 10-14, 15-19, 20-24, etc.). The
rates for the desired age categories are obtained by assuming the rate
specified in the preceding table for each individual age category, and
averaging. For example, the
severely-disabled rate for the age category 15-19 is estimated as:
(0 (for age 15) + 0 (for age 16) + 0 (for age 17)
+ 2.1
(for age 18) + 2.1 (for age 19))/5
= .84 .
Applying this process produces the following table,
which includes prevalences for all of the age
categories used by the DESTINY program. Values
of zero are used for ages below 14 and above 65. In this table, the percentages have been
converted to fractions, since it is fractional rates, not percentage rates,
that are entered into the PARAM program.
Persons with Work Disability (percent)
Age Severely Partially
0-4 0 0
5-9 0 0
10-14 0 0
15-19 .0084 .0156
20-24 .021 .039
25-29 .029 .070
30-34 .029 .070
35-39 .063 .083
40-44 .063 .083
45-49 .110 .124
50-54 .110 .124
55-59 .242 .118
60-64 .242 .118
65-69 0 0
70-74 0 0
75+ 0 0
Although the prevalence data are now available by the
age categories used by the DESTINY system, they cannot be entered in the same
format as above. As discussed, the PARAM
program accepts at most nine different incidence or prevalence values (per
condition). Up to nine values are
specified, and the index of one of these values is specified for each cell of a
stratification table.
In the present case, the data are available by age
category, so the age stratification table is used. The program presents the following prompt:
THE FOLLOWING TYPES OF STRATIFICATION ARE AVAILABLE:
1: NONE
2: AGE
3: SEX
4: RACE
5: AGE X SEX
6: AGE X RACE
7: SEX X RACE
8: AGE X SEX X RACE
9: REGION
10: REGION X RACE
ENTER TYPE OF STRATIFICATION (1-10): ,
to which the user enters a 2 (for stratification by
age). The program then requests:
ENTER 9 INCIDENCE/PREVALENCE RATE(S) (8X.XXXXXXXX): .
For the partial disability condition, there are seven
different values entered in the preceding table -- 0, .0084, .021, .029, .063,
.110, and .242. A total of nine
different values must be entered, so the user responds:
0., .0084, .021, .029, .063, .110, .242, 0., 0. .
Next, it is necessary to specify which of these seven
stratum values is used by each of the 17 age categories. This is done by specifying the stratum index
for each of the 17 age categories. These
are as follows:
Age Stratum Index
0-4 1 (corresponding
to the value 0)
5-9 1
10-14 1
15-19 2 (corresponding
to the value .0084)
20-24 3 (i.e., the
value .021)
25-29 4 (i.e., the value .029)
30-34 4 (i.e., the
value .029)
35-39 5 (i.e., the
value .063)
40-44 5 (i.e., the
value .063)
45-49 6 (i.e., the
value .110)
50-54 6
55-59 7
60-64 7
65-70 1
70-74 1
75+ 1
The program requests:
ENTER 16 INDICES (1 FOR EACH AGE COHORT) EACH OF VALUE
1-9
(16X): .
to which the user responds:
1112344556677111 .
Similarly, for the partial work disability, the user
specifies the stratification type as 2, the nine incidence/prevalence rates as
0, .0156, .039, .070, .083, .124, .118, 0., 0., and the nine stratification indices
as 1112344556677111.
The forms of Appendix B may be used to record the
stratification values and indices, prior to data entry.
The CHECK program may be run to display or print the
entered service-system data, so that it may be reviewed for correctness. Listing 11 presents the CHECK run for this
example.
Listing 12 presents a projection of the work-disabled
population to the year 1990. The
projection is disaggregated by age. The
base-year work-disabled population is also printed out.
In the printout, the acronym WRKDISSV stands for
"Severely Work-Disabled," and the acronym WRKDISPT stands for
"Partially Work-Disabled."
This example is similar to the previous one, since it
deals with the estimation of a specific target population -- in this case,
those enrolled in schools. This example
carries the estimation process a little further, in also estimating the number
of elementary and secondary school teachers.
The number of teachers is estimated for 0-18 year olds, assuming a
student/teacher ratio of 20. The total
salary cost of the teachers is also estimated, assuming an average salary of
$17,200 per year.
As in the previous example, the PARAM program is
executed to develop a new parameter file from the AZ803C.DAT population data
file. The new file is called AZ803CE.DAT
("E" for education). The
Input Option parameter values are the same as in the previous example, i.e.,
Service-System Option = 1.
The target population in this example is all students,
and the served population is all students in elementary and secondary
schools. The service is teaching, the
resource is teachers, and the cost is the dollar cost of the teachers'
salaries.
The target population and service-system parameter
values to be specified to the PARAM program are as follows:
No. of target populations = 1 (i.e,
school students)
Service Population Option = 2 (i.e., service-system
data will be included in the model, and the service population is taken to be
some subset of the target population)
No. of services = 1 (teaching)
No. of resources = 1 (teachers)
No. of cost categories = 1 (salaries)
The names entered for the various model variables are
as follows:
Name of target population: STUDENTS
Name of service population: ELEM/SEC
Name of service: TEACHING
Name of resource: TEACHERS
Name of cost category: SALARIES .
The amount service provided to each served person is
one "unit" of teaching. As
mentioned, the projection will be done assuming a student/teacher ratio of 20,
so that the amount of resources (teachers) expended per student served is
.05. For the projection, an average
teacher salary of $17,200 will be assumed.
The preceding data are entered in response to the
various program requests. At this point,
the structure of the target population and service system has been
specified. What remains is to specify
the incidence/prevalence data for the target population and the service ratios
that specify what proportion of the target population is served.
Table No. 225 of SA81, "School Enrollment and
Rate, by Age, Sex, and Race: 1960 to 1980," provides data on the
proportions of the noninstitutional civilian
population that are enrolled in school.
It is assumed that the state enrollment rates are similar to the
national rates. The enrollment rates do
not vary much by sex or race, so the prevalence of students will be specified
only by age. The following table, which
is extracted from the previous table, presents enrollment rates by age for
1980. As was done in the preceding example,
the rates are adjusted by the factor .972199 to convert to the rates to
proportions of the resident population.
Enrollment Rate
Age Noninst Civ Pop Base Res Pop Base
3-4 .367 .357
5-6 .957 .930
7-13 .993 .965
14-15 .982 .955
16-17 .890 .865
18-19 .464 .451
20-21 .310 .301
22-24 .163 .158
25-29 .093 .090
30-34 .064 .062
The age categories used in this table do not
correspond to the age categories used in the DESTINY model. The estimates for the DESTINY age categories
will be estimated by the same procedure used in the preceding example, viz., by
assuming the rates specified in the preceding table for individual years and
averaging over five-year intervals. For
example, the rate for the 0-4 age category is:
( 0 (for age 0) + 0 (for age 1) + 0 (for age 2)
+ .357 (for age
3) + .357 (for age 4) )/5 = .143 .
Application of this procedure results in the following
table:
Age Enrollment Rate
0-4 .143
5-9 .952
10-14 .963
15-19 .717
20-24 .215
25-29 .090
30-34 .062
35-39 0
40-44 0
45-49 0
50-54 0
55-59 0
60-64 0
65-69 0
70-75 0
75+ 0
These prevalences are
stratified by age, and so, as in the preceding example, they will be specified
to the model using stratification by age.
The nine stratum values are .143, .953, .965, .717, .216, .090, .060,
0.0, and 0.0, and the 16 stratum indices are 1234567888888888.
The next items to be specified are the service ratios
-- the proportion of the target population that is served, by age
category. In this example we are
interested in the students in elementary and secondary schools. It will be assumed that these are all of the
students aged 0-18. Under this assumption
the service ratios are 1.0 for the first three age categories, .874 for the
fourth age category, and zero for all later age categories. The number .874 (for ages 15-19) is obtained
as:
(.955+.865+.865+.451+0 )/(.955+.865+.865+.451+.451)
= .874 .
This computation is based on the assumption that the
numbers of students in each age category (of the cohort 15-19) are identical,
all students through age 18 are served, and no students aged 19 are served.
Age Service Ratio
0-4 1.0 (i.e., all are served)
5-9 1.0
10-14 1.0
15-19 .874
20-24 0
25-29 0
30-34 0
35-39 0
40-44 0
45-49 0
50-54 0
55-59 0
60-64 0
65-69 0
70-75 0
75+ 0
These prevalences are
stratified by age. The nine age-stratum
values are 1.0, .874, and seven zeros.
The 16 age-stratum indices are 1112333333333333.
Listing 13 presents the CHECK run for this example.
Listing 14 presents a projection of the elementary and
secondary school student population by age and region. The projection also shows the projected
number of teachers and salaries by region.
In the printout, the acronym ELEM/SEC stands for
"Elementary and Secondary School Students." Also, in the distribution of teachers and
teachers' salaries by age, "age" refers to age of students.
This example illustrates the use of DESTINY to project
prison admissions and operating cost.
As in the previous examples, the PARAM program is
executed to develop a new parameter file from the AZ803C.DAT population data
file. The new file is named AZ803CP.DAT
("P" for prison population).
The Input Option parameter values are the same as in the previous
example, i.e., Service-System Option = 1.
The approach taken in this example will be somewhat
unusual, in that the target population will be taken to be prison admissions,
rather than prison inmates. The size of
the target population will hence be specified in terms of incidences
(admissions per capita per year), instead of prevalences
(inmate population as a proportion of the resident population). Furthermore, the system will be used to
estimate the expected cost of care until the earliest possible release date
associated with the admissions of each year, rather than the annual cost of
care. The reason for this approach is
that the average time served to parole eligibility is increasing, and it is
desired to project the contingent liability associated with incarceration.
In this example, the service population will be the
sentence-years associated with the admissions.
The service will be incarceration, the resource will be cells, and the
cost will be operating cost per cell.
The reason for defining the service population as sentence-years rather
than admissions (i.e., identical to the target population) is that sentences
vary substantially by sex, but the service, resource, and cost parameters do
not vary (in the DESTINY model) by the demographic features of the person
served. It is necessary to reflect
dependencies on demographic characteristics either in the target population
incidences/prevalences or the service population
service ratios.
The target population and service-system parameter
values to be specified to the PARAM program are as follows:
No. of target populations = 1 (i.e,
prison admissions)
Service Population Option = 2 (i.e., service-system
data will be included in the model, and the service population will be
proportional to the target population)
No. of services = 1 (incarceration)
No. of resources = 1 (cell)
No. of cost categories = 1 (operating cost per cell)
The names entered for the various model variables are
as follows:
Name of target population: ADMIS'NS
Name of service population: SENTYR
Name of service: INCARC'N
Name of resource: CELL
Name of cost category: OP COST .
The service provided to each service population unit (a
sentence-year) is a one-year incarceration.
For each one-year incarceration, the resource expended is a prison cell
(for one year). For each cell, the cost
will be taken as $16,000 (for one year).
The preceding data are entered in response to the various
program requests. At this point, the
structure of the target population and service system has been specified. What remains is to specify the
incidence/prevalence data for the target population and the service ratios that
specify the served population as a proportion of the target population.
The data for this example were obtained from the
Arizona Department of Corrections. The
$16,000 figure cited earlier was the approximate per-inmate operating cost in
1980 (source: Arizona Department of Corrections Information Office).
The following data are available from
Adult
Admissions
Age Male Female
15-19 254
25
20-24 560 25
25-29 345 28
30-34 224 17
35-39 104 8
40-44
55 4
45-49 43 4
50-54
36 2
55-59
16 1
60+
13 0
Total 1,652 114
Dividing these numbers by the
Admission Rate
Age Male Female
15-19 .0020 .00020
20-24 .0042 .00019
25-29 .0029 .00024
30-34 .0021 .00016
35-39 .0013 .00010
40-44 .00082 .00006
45-49 .00070 .00006
50-54 .00060 .00003
55-59 .00026 .00001
60+ .00007 0
These data are stratified by age and sex, and so the
age-by-sex stratification option will be used to enter them into the PARAM
program. At most nine stratification
values are allowed. These values will be taken as 0., .002, .004, .003, .001,
.0003, .00007, .0002, and .00002. The
index values are 1112342555567777 for males and 1118888777991111 for
females. Note that there are more than
nine different values in the incidence table, but that a maximum of nine
different stratum values is allowed. In
this case, an approximation is made, and the actual incidences are represented
by nearby values. This approximation
will have little effect on the overall estimate of admissions, but projections
should not be made by age and sex jointly (since individual cell incidences are
not correct for some of the smaller cells).
Service ratios (the number of sentence-years per
admission) will be computed from the average number of months to parole
eligibility. For men, this average is
35.8, corresponding to 3.0 years. For
females, the average is 27.7, corresponding to 2.3 years. These service ratios are stratified by sex,
and so the stratification-by-sex data entry option will be used. The stratum values are 3.0 (male) and 2.3
(female).
Listing 15 presents the CHECK run for this example.
Listing 16 presents a projection of admissions and
obligated cost associated with the admissions.
Recall that the term "cost" in this example is the total
sentence-long operating cost associated with (obligated by) the admissions of a
particular year, not just the expense during that year. (To estimate the expense for particular
years, the model should be respecified with inmates
as the target population and service population, instead of admissions as the
target population and sentence-years as the service population.)
In the printout, the acronym ADMIS'NS denotes
"admissions," SENTYR denotes "sentence-years," CELL denotes
"prison cell," and OP COST denotes the cost of care for inmates
(exclusive of capital costs).
In an actual policy analysis, a number of runs similar
to the example would be required. For
example, to determine the effect of sentencing only violent criminals to
prison, and at different sentence lengths from current practice, a run would be
required which included not just one but several inmate ("target")
populations, each representing a different level of violence and past behavior.
This example illustrates the projection (by year) of
bed needs for short-term care (less than 30 days) and for long-term care (30
days or more). This example illustrates
the application of DESTINY to estimate four different target populations
simultaneously.
The PARAM program is run to construct a new parameter
file from the AZ803C.DAT file. The new
file is called AZ803CH.DAT ("H" for health). In this example,
there will be four target populations but no service population. The four target populations are
short-term-stay hospital beds, nursing-home beds, psychiatric-hospital beds,
and mental-hospital beds.
The target population and service-system parameter
values to be specified to the PARAM program are as follows:
No. of target populations = 4 (i.e,
four bed types)
Service Population Option = 0 (i.e., no service-system
data will be included in the model)
The names entered for the various model variables are
as follows:
Names of target population: ST BEDS, NH BEDS, PSY
BEDS, and MH BEDS
The preceding data are entered in response to the
various program requests. The
incidence/prevalence data for the target populations will now be specified.
The need for beds will be measured by applying the
national number of short-term-stay beds per 100,000 population
to the
Data on short-term-stay beds are found in Table 179 of
SA81, "Hospital Utilization Rates, by Sex and Age of Patient: 1965 to
1979." The rates are relative to
the total civilian noninstitutional population; as
before, they are converted to the resident population base by multiplying by
.972199
Beds/100,000
Age Civ noninst pop Res pop
Under
1 360 350.0
1-4 93 90.4
5-14 58 56.4
15-24
180 175.0
25-34 249 242.1
35-44 262 254.7
45-64 440 427.8
65+ 1,146 1,114.1
The rate for the 0-4 age category is estimated as
.2(350) + .8(90.4) = 142.3. Using the
stratification-by-age option for data entry, the nine age stratum values are
(dividing by 100,000) .00142, .00056, .00175, .00242, .00255, .00428, .01114,
0. and 0., and the 16 stratification indices are 1223344556666777.
Data for long-term-stay beds are found in Table 182
SA81, "Long-Term Care Institutions -- Summary: 1976," a portion of
which is shown below:
Number of Residents (US, 1976)
Age
Nursing Home Psychiatric Mentally Handicapped
0-17 9,000 28,000 56,000
18-64 154,000 32,000 125,000
65+ 989,000 5,000 6,000
Additional data for nursing homes are found in Table
184 SA81, "Nursing and Personal Care Homes -- Selected Characteristics of
Homes and Residents, and Primary Sources of Payment: 1964-1977," a portion
of which is shown below (excluding personal care homes without nursing):
Number of Residents (US, 1973-74)
Age Male Female
Under
65 52,000 62,000
65-74 65,000 98,000
75-84 102,000 283,000
85+ 98,000 315,000
From Table 30 SA81, the total population in the
various age categories of the preceding tables may be determined. The proportion male is taken from the Coale-Demeny model life table for the
Total Est 1974
1980 Prop Res
Pop Est
1976
Age Pop
Male Male
Female Male Female Res Pop
0-17 63.7 .508
32.4 31.3 30.52 29.48
61.18
18-64 137.7 .49
67.5 70.2 63.58 66.12
132.26
65-69 8.8 .43
3.78 5.02 3.56
4.73 |
70-74 6.8 .41
2.79 4.01 2.63
3.78 24.49
75+ 9.9
.34 3.37 6.53
3.17 6.15 |
226.9 226.9
213.72 217.94
Dividing the populations into the numbers of residents
produces the following results.
Proportion of Population in Indicated
Facility, 1976
Nursing Mentally
Age Home
Psychiatric Handicapped
0-17 .00015 .00046 .00092
18-64 .00117
.00024 .00095
65+ .0404
.00020 .00024
Proportion of Population in Nursing Homes, 1974
Age Male Female
0-64 .00055 .00065
65-74 .0105 .0115
75+ .063 .097
Combining the preceding results for nursing homes
produces the following table:
Proportion
of Population in Nursing Homes, 1974 and 1976
Age Male Female
0-17 .00015
.00015
18-64 .0012
.0012
65-74 .011
.012
75+ .063 .097
Residents of nursing homes, psychiatric, and mentally
handicapped facilities will be used as a proxy for beds.
The prevalence data for nursing home beds are
stratified by age and sex, and so they will be entered using the corresponding
option. The nine stratum values are
.00015, .0012, .011, .063, .00015, .0012, .012, .097, and 0. The 16 stratification indices for males are
1111222222222334, and the indices for females are 1111222222222556.
The prevalence data for psychiatric facility beds are
stratified by age. The nine
stratification values are .00046, .00024, .00020, and six zeros. The stratification indices are 1111222222222333.
The prevalence data for mentally handicapped
facilities are also stratified by age.
The stratification values are .00092, .00095, .00024, and six
zeros. The stratification indices are
1111222222222333.
Listing 17 presents the CHECK run for this example.
Listing 18 presents a projection of the need for the
four types of beds by year to 1990.
In the printout, ST BEDS refers to beds in short-stay
hospitals, and the acronyms NH BEDS, PSY BEDS, and NH BEDS refer to beds in
long-term care facilities (nursing homes, psychiatric facilities, and
facilities for the mentally handicapped, respectively).
This example illustrates the use of the DESTINY
program to project service levels, personnel, and budget levels required to
provide social services to the elderly.
The data used in this example are hypothetical. In a real application, the service ratios
would be estimated from client caseload data, and the unit of service, unit of
resource, and unit cost data would be estimated from program administrative
records.
This example will build on the three-race, 14-region
population data file for
The target population and service-system parameter
values to be specified to the PARAM program are as follows:
No. of target populations = 1 (i.e,
the elderly)
Service Population Option = 2 (i.e., service-system
data will be included in the model, and the service population will be
proportional to the target population)
No. of services = 7
No. of resources = 3
No. of cost categories = 3
The names entered for the various model variables are
as follows:
Names of target population: ELDERLY
Name of service population: ELDR(SV)
Names of services: COUNSLNG, CHORE SV, HOMEMAKR,
SUBSCARE, DAY CARE, TRANSPRT, OTHER
Names of resources: COUNSELR, PURCHSVC, PAYMENTS
Names of cost categories: DIRCTSV$, PURCHSV$, PAYMENT$
.
The preceding data are entered in response to the
various program requests. The incidence/prevalence
data for the target population will now be specified. As mentioned, hypothetical data will be used
for this example. This example assumes
that approximately five percent of the elderly population requires social
services (specifically, 3% of those aged 65-69, 5% of those aged 70-74,and 7%
of those aged 75+).
Target Population Parameters
In the present example, the target population is all
persons aged 65 or older. The prevalence
of the target population in the general population is hence to be specified in
terms of age categories. The data are
hence entered into the program by selecting stratification option number 2
(ST2), in which a separate rate is specified for each five-year age category. Under this option, the user may enter up to
nine different prevalences. In the present example, however, only two are
needed: the prevalence is 0.00 (0%) for
all persons whose age is less than 65, and 1.00 (100%) of those whose age is 65
or over.
The following table indicates the nine prevalences entered to the PARAM program (only the first
two are of concern in this example:
Index Rate
1 0.00
2 1.00
3 0.00
4 0.00
5 0.00
6 0.00
7 0.00
8 0.00
9 0.00
Next needs to be specified which of the preceding
rates applies to each of the sixteen age categories. The first rate (0.00, Index = 1) applies to
the first 13 age categories (ages 0 - 64), and the second rate (1.00, Index -
2) applies to the last three age categories (ages 65+.) The list of indexes to be entered is hence as
follows:
Stratum
(Age Category) Index
0-4 1
5-9 1
10-14 1
15-19 1
20-24 1
25-29 1
30-34 1
35-39 1
40-44 1
45-49 1
50-54 1
55-59 1
60-64 1
65-69 2
70-74 2
75+ 2
Service Population Parameters
The service population is assumed to be 3% of the
target population aged 65-69, 5% of the target population aged 70-74, and 7% of
the target population aged 75+. Once
again, since these prevalences depend only on age,
stratification option ST2 is used. There
are four rates of interest: 0.00 (0%), .03 (3%), .05 (5%), and .07 (7%).
The following table indicates the nine prevalences entered to the PARAM program (only the first
four of which are of interest in this example.):
Index Rate
1 0.00
2 0.03
3 0.05
4 0.07
5 0.00
6 0.00
7 0.00
8 0.00
9 0.00
The four prevalences apply
to the last four age categories, in order.
The list of indexes to be entered to the program:
Stratum
(Age Category) Index
0-4 1
5-9 1
10-14 1
15-19 1
20-24 1
25-29 1
30-34 1
35-39 1
40-44 1
45-49 1
50-54 1
55-59 1
60-64 1
65-69 2
70-74 3
75+ 4
Service Parameters
The following table indicates the average number of
units of service of each type provided to each served client per year:
Average
Number of Service Units Per Case Per Year
No. of Service Units
Service per Case per Year
S1. Counseling 2 hours
S2. Chore
Services 16 dollars
S3. Homemaker
Services
750 dollars
S4. Substitute
Care
12 dollars
S5. Day Care 7 dollars
S6. Transportation
10 dollars
S7. Other
10 dollars
In this example, counseling is the only
"direct" service, i.e., service provided by the state social service
staff. All of the other services are
purchased from "service providers," and the unit of service is taken
to be equal to one dollar.
Resource Parameters
The average number of service units per served client
is as specified in the following table:
Average
Number of Resource Units Per Service Unit
(Service
types as defined in the preceding table)
No. of Resource
Units per
Service Unit (by
Service Type)
Resource S1 S2
S3 S4 S5
S6 S7
R1. Counselor 1 0 0 0 0 0 0
R2. Dollar
(Purchase) 0 1 1 1 1 .5 .5
R3. Dollar
(Payment) 0 0 0 0 0 .5 .5
In this example, half of the TRANSPRT service (S6) is
a payment to the client, and half is a payment to the service provider. The same is true of the OTHER service.
Cost Parameters
It is assumed that the cost of counselor service is
$15 per hour. Since the other services
are in fact dollars, their cost is $1 per dollar. The following table summarizes these costs:
Average
Cost Per Resource Unit
(Resource
types as defined in the preceding table)
Cost per Resource
Unit
(by resource
type)
Cost Category
R1 R2 R3
C1. Direct
Service 15
0 0
C2. Purchased
Service 0
1 0
C3.
Payment 0 0 1
Listing 19 presents the CHECK run for this example.
Listing 20 presents a projection of the social
services served population, services, resources, and costs. In this example we show a three-year-ahead
projection, as opposed to the ten-year-ahead projections that were illustrated
in the other examples.
The printout shows the services, resources, and budget
required to provide services to the served population.
The DESTINY program could be used to estimate the
changes in the budget that would occur if different service levels or different
service costs were adopted. Used in this
way, DESTINY is an ideal tool in the evaluation of alternative strategies for
rationing social services.
The example illustrates several of the different types
of crosstabulations that can be constructed by the
DESTINY program. The total number of
possible crosstabs is very large, and typically only
a few of them would be selected by the user for printout. Up to nine demographic distributions or crosstabs may be constructed for each of the many variables
forecast by the program (general population, target population (the elderly),
seven social services, three resources, and three cost categories). These include crosstabs
by age, sex, race, age by sex, age by race, sex by race, age by sex by race,
region, and race by region. In addition,
nine different service-system-related distributions or crosstabs
may be specified:
o distribution
of services by type
o distribution
of resources by type
o distribution
of costs by type
o distribution
of services by served population
o distribution
of resources by served population
o distribution
of cost by served population
o distribution
of resources by services
o distribution
of costs by services
o distribution
of costs by resources
In this example, we present only a small fraction of
the possible output tables.
Data such as these may be used to back up legislative
budget requests, to prepare Comprehensive Annual Services Program plans, or to
estimate staffing levels. Additional
runs could reveal the budgetary impact of changes in service levels or costs.
1. DESTINY Planning and Forecasting System:
Description of Capabilities, Joseph George Caldwell,
There are two types of information required by the
PARAM program, in order to construct a parameter file for use by the DESTINY
package -- demographic information and service-system information. The demographic information consists of a
number of demographic parameters, such as birth and death rates, and some
demographic variables, such as population totals by age, sex, race, and
geographic region. The service-system
information consists of incidences or prevalences for
target populations of interest, service ratios, and various service, resource,
and cost parameters.
Demographic Specification
The demographic data (parameters and variables)
required by the DESTINY program are very basic quantities, and most of them are
available at the national and state levels.
For the
1. Statistical
Abstract of the United States (annual) (various years)
2. Vital
Statistics of the United States (annual), Volume I, Natality
and Volume II, Mortality, Part A
3. Census of
Population (decennial)
At the state level, major data source is the County
and City Data Book supplement to the Statistical Abstract; it is
published in various years. Each state
publishes state-level versions of the statistical abstract and vital statistics
reports; the 1980 Census data are available at the state level as well.
The Census of Population presents detailed
population breakdowns by age, sex, race, and geographic region. The Vital Statistics and Statistical
Abstract present demographic parameters such as birth and death rates.
Most countries other than the
1. World Fertility Survey
2. United Nations Demographic Handbook
The DESTINY program population projections are based on
a five-year time interval, and the required parameters refer to future
five-year periods. The program makes
projections corresponding to whatever demographic assumptions the user wishes
to specify about the future, and the user's specified values may differ from
historical values. If historical data
are used to determine these parameters, the average values over the last five
years should normally be used. If data
for a recent five-year period are not available, data for the latest available
year may be used. If historical values
fluctuate substantially from year to year, a several-year average would usually
be preferable to an estimate based on a single year. If a demographic parameter appears to be
changing over time (e.g., a declining trend in the birth rate), the value
entered to DESTINY may be based on the five-year average of values derived from
a statistical time-series forecasting model.
Even in the
The user must decide whether to characterize the
population survival rates by the Infant Mortality Rate (IMR) or the Expectation
of Life at Birth (ELB), corresponding to Life Table Option parameter value
equal to 1 or to 2, respectively. As a
general rule, use Option 1 (i.e., specify the IMR) for countries in which the IMR
is high, and the ELB for countries in which the IMR is low. For whichever option the user specifies, the
CHECK program will print out the value of the non-specified parameter,
according to the Coale-Demeny "West" model
life table.
For example, suppose that the user has specified Life
Table Option 1 (specify the IMR), but he is particularly interested in
projections of the elderly population.
If the CHECK printout indicates that the user-specified value of the IMR
implies an ELB value that is quite different from the observed value, it would
be advisable to respecify the model in terms of Life
Table Option 2, and enter the desired Expectation of Life at Birth.
Service-System Parameters
Because of the tremendous variety of target
populations and service systems to which the DESTINY program may be applied, it
is not possible to identify standard sources from which information pertaining
to these model aspects may be obtained.
With regard to target populations, local-level data are often not
available on incidences and prevalences, and national-
or regional-level data, by age, sex, or race must be used. Such data are available in published form
from nationwide surveys, such as the Disability Survey of 1972 or the National
Health Interview Survey.
With regard to service-system data, most health or
social service programs are operated at the state or local level, and data on
program services, resources, and costs are often available from administrative
records maintained at these levels. A
major problem that may be encountered is that the DESTINY program needs these
parameters on an annual basis (e.g., average number of cases per year, average
number of service units per case per year), and many organizations do not
collect client caseload data this way.
This situation is changing, however, as the awareness of the need to do
planning based on parametric models is increasing.
This appendix includes data entry forms for use in
collecting the data required by the PARAM and CHECK programs. The data entry forms list the data in order
of entry to the PARAM program. To assist
the user in remembering where each data element was obtained, space is provided
to record the "source" of each element.
The data entry forms do not describe the meaning of
the various options that are available for each input parameter. Those descriptions are presented in the text
of this user's manual. The forms do
specify, however, the format required for each data element.
PARAM
Form 1: Basic File Structure Parameters
Parameter File Name (12X): ________________
General Population Description
(8OX):_________________________
______________________________________________________________
Base Year (4X):________________
Basic File Structure Parameters:
P1: Number of
Races (1-3):_____________________
P2: Number
of Regions (1-14):__________________
P3:
Demographic Parameter Option (1 or 2):_____
P4: Life
Table Option (1 or 2):________________
P5:
External Migration Parameter Option
(0, 1, or 2):_______
P6:
Internal Migration Parameter Option
(0 or
1):_______
P7: Service
System Option (0 or 1):____________
Names of Races (8X):RA1__________
RA2__________
RA3__________
Names of Regions (8X):RE1_______________ RE8_______________
RE2_______________
RE9_______________
RE3_______________
RE10______________
RE4_______________ RE11______________
RE5_______________
RE12______________
RE6_______________
RE13______________
RE7_______________
RE14______________
PARAM
Form 2: Demographic Parameters and Variables
for Race =
__________ (one complete set needed for each race)
Total Fertility Rate(s)
Source:__________________________________________________
If P3 = 1,
specify 1 TFR (X.XXX):__________
If P3 = 2, specify
10 TFRs (10X.XXX), one for each 5-year projection
period:
____,____,_____,_____,_____,_____,_____,_____,_____,_____
Fertility Age Distribution(s)
Source:__________________________________________________
If P3 = 1, specify
1 FAD (6X.XXX):
_________,_________,_________,________,________,_________
If P3 = 2,
specify 10 FADs (6X.XXX), one for each 5-year
projection period:
_________,_________,_________,________,________,_________
_________,_________,_________,________,________,_________
_________,_________,_________,________,________,_________
_________,_________,_________,________,________,_________
_________,_________,_________,________,________,_________
_________,_________,_________,________,________,_________
_________,_________,_________,________,________,_________
_________,_________,_________,________,________,_________
_________,_________,_________,________,________,_________
_________,_________,_________,________,________,_________
Infant Mortality Rate(s) (required if P4 = 1)
Source:__________________________________________________
If P3 = 1,
specify 1 IMR (XXX.XX):__________
If P3 = 2, specify
10 IMRs (10XXX.XX), one for each 5-year projection
period:
_____,_____,_____,_____,_____,_____,_____,____,____,_____
Expectation(s) of Life at Birth (required if P4 = 2)
Source:__________________________________________________
If P3 = 1,
specify 1 ELB (XX.XX):__________
If P3 = 2,
specify 10 ELBs (10XX.XX), one for each 5-year
projection period:
_____,_____,_____,_____,_____,_____,_____,____,____,_____
Base-Year Population
Source:__________________________________________________
For Males
(8XXXXXXXXX.):
_____,_____,______,______,______,______,______,______(CR)
_____,_____,______,______,______,______,______,______
For Females
(XXXXXXXXX.):
_____,_____,______,______,______,______,______,______(CR)
_____,_____,______,______,______,______,______,______
Base-Year Infant Mortality Rate (XXX.XX):____________
Source:__________________________________________________
Base-Year Birth Rate (XXX.XX):____________
Source:__________________________________________________
Base-Year Death Rate (XXX.XX):____________
Source:__________________________________________________
Population Ten Years Prior to Base Year (XXXXXXXXX.):
___________ Source:_____________________
Infant Mortality Rate Ten Years Prior to Base Year (XXX.XXXX):
___________
Source:_____________________
Birth Rate Ten Years Prior to Base Year (XXX.XXXX):
___________
Source:_____________________
Death Rate Ten Years Prior to Base Year (XXX.XX):
___________
Source:_____________________
External Migration Parameters (data required only if P5 is
greater than
zero)
Source:__________________________________________________
If P5 =
1:
Annual
Migration Rate (XXXX.XXX)__________________
Annual
Migration Number (XXXXXXXXX.)_____________
If P5 =
2:
Specify ten annual migration rates (10XXXX.XXX), one
for each 5-year projection period:
_____,_____,_____,_____,_____,_____,_____,____,____,_____
Specify ten annual migration numbers (8XXXXXXXXX.),
one for each 5-year projection period:
_____,_____,_____,_____,_____,_____,_____,____,____,_____
Regional Population (data required only if P2 is greater than 1)
Source:__________________________________________________
______,______,______,______,______,_______,_______,______
______,______,______,______,______,_______,_______,______
Regional Population Ten Years Prior to Base Year (data required only if P2 is greater than 1)
Source:__________________________________________________
______,______,______,______,______,_______,_______,______
______,______,______,______,______,_______,_______,______
Internal Migration Parameters (Data required only if P6 is greater than zero)
Source:__________________________________________________
Specify one annual internal migration rate for each
region (8XXXX.XXX):
______,______,______,______,______,______,______,______
______,______,______,______,______,______
Specify one annual internal migration amount (number)
for each region (8XXXXXXXXX.):
______,______,______,______,______,______,______,______
______,______,______,______,______,______
PARAM
Form 3: Service-System Parameters
(Required
only if P7 = 1)
Service-System Structural Parameters
S1: Number
of Target Populations (1-4):__________
S2: Service
Population Option (0, 1, or 2):______
S3: Number
of Services (0-10):___________________
S4: Number
of Resources (0-7):___________________
S5: Number
of Cost Categories (0-4):_____________
Names of Target Populations (8X):
TP1:_______________
TP2:_______________
TP3:_______________
TP4:_______________
Names of Service Populations (8X):
SP1:_______________
SP2:_______________
SP3:_______________
SP4:_______________
Names of Services (8X):
S1:________________
S2:________________
S3:________________
S4:________________
S5:________________
S6:________________
S7:________________
S8:________________
S9:________________
S10:_______________
Names of Resources (8X):
R1:________________
R2:________________
R3:________________
R4:________________
R5:________________
R6:________________
R7:________________
Names of Cost Categories (8X):
C1:________________
C2:________________
C3:________________
C4:________________
Service
Parameters
Service Population Service Type
S1 S2 S3
S4 S5 S6
S7 S8 S9 S10
Name Names:___ ___ ___ ___ ___ ___ ___ ___
___ ___
SP1:__________
___ ___ ___ ___ ___ ___ ___ ___ ___ ___
SP2:__________
___ ___ ___ ___ ___ ___ ___ ___ ___ ___
SP3:__________
___ ___ ___ ___ ___ ___ ___ ___ ___ ___
SP4:__________
___ ___ ___ ___ ___ ___ ___
___ ___ ___
Note: Each table entry (XXXXX.XXXX) is entered to the
program separately, reading across the first row, then the second row, etc.
Resource
Parameters
Service Type Resource Type
R1 R2
R3 R4 R5
R6 R7 R8
R9 R10
Name Names:___ ___ ___ ___ ___ ___ ___ ___
___ ___
S1:__________
___ ___ ___ ___ ___ ___ ___ ___ ___ ___
S2:__________
___ ___ ___ ___ ___ ___ ___ ___ ___ ___
S3:__________
___ ___ ___ ___ ___ ___ ___ ___ ___ ___
S4:__________
___ ___ ___ ___ ___ ___ ___ ___ ___ ___
S5:__________
___ ___ ___ ___ ___ ___ ___ ___ ___ ___
S6:__________
___ ___ ___ ___ ___ ___ ___ ___ ___ ___
S7:__________
___ ___ ___ ___ ___ ___ ___ ___ ___ ___
S8:__________
___ ___ ___ ___ ___ ___ ___ ___ ___ ___
S9:__________
___ ___ ___ ___ ___ ___ ___ ___ ___ ___
S10:_________
___ ___ ___ ___ ___ ___ ___ ___ ___ ___
Note: Each table entry (XXXXX.XXXX) is entered to the
program separately, reading across the first row, then the second row, etc.
Cost
Parameters
Resource Type
Name Names:_________ _________ _________
_________
R1:__________
_________ _________ _________ _________
R2:__________
_________ _________ _________ _________
R3:__________
_________ _________ _________ _________
R4:__________
_________ _________ _________ _________
R5:__________
_________ _________ _________ _________
R6:__________
_________ _________ _________ _________
R7:__________
_________ _________ _________ _________
PARAM
Form 4: Target Population Parameters
for
Target Population = ______________
(Required only if P7 = 1, in which case one form is
needed for each target population.)
Data Source:__________________________________________
Stratification Option:
Specify 1
Option:
___ST1 No stratification (single
rate for entire
population)
___ST2 Stratify by Age
___ST3 Stratify by Sex
___ST4 Stratify by Race
___ST5 Stratify by Age x Sex
___ST6 Stratify by Age x Race
___ST7 Stratify by Sex x Race
___ST8 Stratify by Age x Sex x
Race
___ST9 Stratify by Region
___ST10
Stratify by Region x Race
Enter data in the section below corresponding to the
Stratification Option selected above.
Option ST1: No Stratification
Specify a
single rate for the entire population: _________
Option
ST2: Stratification by Age
Age
Category Rate
0-4 ______
5-9 ______
10-14 ______
15-19 ______
20-24 ______
25-29 ______
30-34 ______
35-39 ______
40-44 ______
45-49 ______
50-54 ______
55-59 ______
60-64 ______
65-69 ______
70-74 ______
75+ ______
Option
ST3: Stratification by Sex
Sex Rate
Male ______
Female ______
Option
ST4: Stratification by Race
Race Rate
RA1______ ______
RA2______ ______
RA3______ ______
Option
ST5: Stratification by Age x Sex
Sex = Male
Age
Category Rate
0-4 ______
5-9 ______
10-14 ______
15-19 ______
20-24 ______
25-29 ______
30-34 ______
35-39 ______
40-44 ______
45-49 ______
50-54 ______
55-59 ______
60-64 ______
65-69 ______
70-74 ______
75+ ______
Sex = Female
Age
Category Rate
0-4 ______
5-9 ______
10-14 ______
15-19 ______
20-24 ______
25-29 ______
30-34 ______
35-39 ______
40-44 ______
45-49 ______
50-54 ______
55-59 ______
60-64 ______
65-69 ______
70-74 ______
75+ ______
Option
ST6: Stratification by Age x Race
Race =
RA1__________
Age
Category Rate
0-4 ______
5-9 ______
10-14 ______
15-19 ______
20-24 ______
25-29 ______
30-34 ______
35-39 ______
40-44 ______
45-49 ______
50-54 ______
55-59 ______
60-64 ______
65-69 ______
70-74 ______
75+ ______
Race =
RA2__________
Age
Category Rate
0-4 ______
5-9 ______
10-14 ______
15-19 ______
20-24 ______
25-29 ______
30-34 ______
35-39 ______
40-44 ______
45-49 ______
50-54 ______
55-59 ______
60-64 ______
65-69 ______
70-74 ______
75+ ______
Race =
RA3__________
Age
Category Rate
0-4 ______
5-9 ______
10-14 ______
15-19 ______
20-24 ______
25-29 ______
30-34 ______
35-39 ______
40-44 ______
45-49 ______
50-54 ______
55-59 ______
60-64 ______
65-69 ______
70-74 ______
75+ ______
Option
ST7: Stratification by Sex x Race
Race =
RA1__________
Sex Rate
Male ______
Female ______
Race =
RA2__________
Sex Rate
Male ______
Female ______
Race =
RA3__________
Sex Rate
Male ______
Female ______
Option
ST8: Stratification by Age x Sex x Race
Race =
RA1__________
Sex = Male
Age Category Rate
0-4 ______
5-9 ______
10-14 ______
15-19 ______
20-24 ______
25-29 ______
30-34 ______
35-39 ______
40-44 ______
45-49 ______
50-54 ______
55-59 ______
60-64 ______
65-69 ______
70-74 ______
75+ ______
Sex = Female
Age
Category Rate
0-4 ______
5-9 ______
10-14 ______
15-19
______
20-24 ______
25-29 ______
30-34 ______
35-39 ______
40-44 ______
45-49 ______
50-54 ______
55-59 ______
60-64 ______
65-69 ______
70-74 ______
75+ ______
Race =
RA2__________
Sex = Male
Age
Category Rate
0-4 ______
5-9 ______
10-14 ______
15-19 ______
20-24 ______
25-29 ______
30-34 ______
35-39 ______
40-44 ______
45-49 ______
50-54 ______
55-59 ______
60-64 ______
65-69 ______
70-74 ______
75+ ______
Sex = Female
Age
Category Rate
0-4 ______
5-9 ______
10-14 ______
15-19 ______
20-24 ______
25-29 ______
30-34 ______
35-39 ______
40-44 ______
45-49 ______
50-54 ______
55-59 ______
60-64 ______
65-69 ______
70-74 ______
75+ ______
Race =
RA3__________
Sex = Male
Age Category Rate
0-4 ______
5-9 ______
10-14 ______
15-19 ______
20-24 ______
25-29 ______
30-34 ______
35-39 ______
40-44 ______
45-49 ______
50-54 ______
55-59 ______
60-64 ______
65-69 ______
70-74 ______
75+ ______
Sex = Female
Age
Category Rate
0-4 ______
5-9 ______
10-14 ______
15-19 ______
20-24 ______
25-29 ______
30-34 ______
35-39 ______
40-44 ______
45-49 ______
50-54 ______
55-59 ______
60-64 ______
65-69 ______
70-74 ______
75+ ______
Option
ST9: Stratification by Region
Region Rate
RE1_________ ______
RE2_________ ______
RE3_________ ______
RE4_________ ______
RE5_________ ______
RE6_________ ______
RE7_________ ______
RE8_________ ______
RE9_________ ______
RE10________ ______
RE11________ ______
RE12________ ______
RE13________ ______
RE14________ ______
Option
ST10: Stratification by Region x Race
Race =
RA1___________
Region Rate
RE1_________ ______
RE2_________ ______
RE3_________ ______
RE4_________ ______
RE5_________ ______
RE6_________ ______
RE7_________ ______
RE8_________ ______
RE9_________ ______
RE10________ ______
RE11________ ______
RE12________ ______
RE13________ ______
RE14________ ______
Race =
RA2___________
Region Rate
RE1_________ ______
RE2_________ ______
RE3_________ ______
RE4_________ ______
RE5_________ ______
RE6_________ ______
RE7_________ ______
RE8_________ ______
RE9_________ ______
RE10________ ______
RE11________ ______
RE12________ ______
RE13________ ______
RE14________ ______
Race =
RA3___________
Region Rate
RE1_________ ______
RE2_________ ______
RE3_________ ______
RE4_________ ______
RE5_________ ______
RE6_________ ______
RE7_________ ______
RE8_________ ______
RE9_________ ______
RE10________ ______
RE11________ ______
RE12________ ______
RE13________ ______
RE14________ ______
PARAM
Form 5: Service Population Parameters
for
Service Population = __________________
(Needed
only if P7 = 1 and S2 = 2, in which
case
one form is needed for each service
population.)
Data
Source:__________________________________________________
Stratification Option:
Specify 1
Option:
___ST1 No stratification (single
rate for entire
population)
___ST2 Stratify by Age
___ST3 Stratify by Sex
___ST4 Stratify by Race
___ST5 Stratify by Age x Sex
___ST6 Stratify by Age x Race
___ST7 Stratify by Sex x Race
___ST8 Stratify by Age x Sex x
Race
___ST9 Stratify by Region
___ST10
Stratify by Region x Race
Enter data in the section below corresponding to the
Stratification Option selected above.
Option
ST1: No Stratification
Specify a
single rate for the entire population:_________
CHECK Form 1
(This form is needed only if the CHECK program is used
to adjust the service-system parameters.)
Actual Base-Year PROJ Base-Year
Actual
Target Population Value Value Ratio = PROJ
TP1______________
___________ __________ _________
TP2______________
TP3______________
TP4______________
Service Population
SP1_______________
SP2_______________
SP3_______________
SP4_______________
Service
S1________________
S2________________
S3________________
S4________________
S5________________
S6________________
S7________________
S8________________
S9________________
S10_______________
Resource
R1________________
R2________________
R3________________
R4________________
R5________________
R6________________
R7________________
Cost
C1________________
C2________________
C3________________
C4________________
Demographic Projection Equations
This Appendix presents the basic demographic equations
which define the cohort-component method for making population
projections. Only a summary description
of the demographic equations is presented here.
For detailed discussion of the cohort-component method, refer to a
demographic text such as:
Shryock, Henry S., Jacob S. Siegel and Associates,
The
Methods and Materials of Demography, Fourth
Printing
(rev.), US Bureau of the Census, US
Government Printing Office,
The formulas presented below correspond to External
Migration Option 1 and Internal Migration Option 0. In the model, the complete set of formulas is
used once for each race represented in the model, with appropriate changes in
the values of the parameters.
The following notation is introduced. The index t refers to time. The index k refers to five-year age
cohort. There are sixteen age cohorts,
first one being ages 0-5, and the last being ages 75+.
TFRt =
total fertility rate at time t (the average
number of children born to a woman in her
lifetime)
FADt(k) = fertility age distribution density
function
(probability that a woman giving birth belongs
to age cohort k) at time t
Stj(1) = probability at time t that an infant of sex
j
survives to age 1 (j = 1, 2)
Stj(k) = probability that a person of sex j in cohort k-1
alive at time t survives to time t+5 (k = 2, 3,
..., 17; j = 1, 2)
Stj* = (Stj(k)
+ Stj+5(k))/2
IMt =
number of immigrants in time t to time
t+5
EMt =
rate of emigration in time period t to t+5
(number of emigrants divided by the total
population)
Pt(k) = total population in age cohort k at time t
Rt(m) =
population in region m at time t
BSRt =
birth sex ratio (proportion of newborns that
are males)
BIRt =
births in time period t to t+5
In terms of the preceding notation, the following
formulas define the population at the time t+5, given the population at time t.
1. Survivors, Age Cohorts 2-15:
PSt+5j(k)
= Ptj(k) Stj*(k+1) (k=2,3,...,16)
2. Survivors, Last Age Cohort:
PSt+5j(16)
= PSt+5j(16) Stj*(17)
3. Births
9
BIRt = TFRt
Σ FAD(k) (Pt2(k) + PSt+52(k))/2
k=4
4. Survivors, First Age Cohort
PSt+5j(1)
= BIRt Stj*(1)
5. Total Survivors Plus Births
TS = Σ PSt+5j(k)
j,k
6. External Migration (Option 1)
Total
Net Migration = TM = IMt - EMt TS
F = 1
+ TM/TS
Pt+5j(k)
= PSt+5j(k) F
7.
Total Population at Time t
TP = Σ Ptj(k)
j,k
8. Internal Migration (Option 0)
Rt+5(m)
= Rt(m) (TS + TM)/TP
External Migration Options 2-4 and Internal Migration
Option 1 are similar to the above.
Service-System Parameter Adjustment Equations
In the CHECK program, the user has the option of
entering an adjustment factor, or calibration factor, for each target
population, service population, service, resource, and cost total that the PROJ
program computes and prints. Each
adjustment factor is the ratio of the actual (observed) base-year level of each
quantity to the base-year level estimated by PROJ.
After the user enters the adjustment factors, the
CHECK program modifies each incidence, service ratio, service, resource, and
cost parameter, and creates a new parameter file containing the modified
parameters. The parameters are modified
so that the base-year estimates printed by the PROJ program will each be multiplied
by the adjustment factor. The formulas
which the CHECK program uses to modify the parameters are as follows:
tpR' = fRtp tpR (R = 1,2,...,ntp)
spR' = fRsp
spR1/fRtp) (R = 1,2,...,ntp)
skR' = fks
skR1/fRsp) (k =
1,2,...,ns; R = 1,2,...,ntp)
rjk' = fjr rjk
(1/fks) (j = 1,2,...,nr; k = 1,2,...,ns)
c'ij = fic cij
(1/fjr) (i = 1,2,...,nc; j = 1,2,...,nr)
where
tpR = old incidence
tpR' = new incidence
spR = old service
ratio
spR' = new service
ratio
skR = old number of units of service type k per
served
case of type R
skR' = new number of units of service type k per
served
case of type R
rjk =
old number of units of resource type j per unit
of service
type k
rjk' =
new number of units of resource type j per unit
of
service type k
cij =
old number of dollars of cost type i per unit of
resource type j
cij' =
new number of dollars of cost type i per unit of
resource type j
fRtp = adjustment factor for target population R
fRsp = adjustment factor for service population R
fks
= adjustment factor for service type k
fjr
= adjustment factor for resource type j
fic = adjustment factor for cost type i
ntp =
number of target populations
=
number of service populations
ns = number of service types
nr = number of resource types
nc =
number of cost categories.
Computer Program Output Listings
1. CHECK Run for Example 1 (National Population
Projection,
Single-Race Model)................................ 157
2. PROJ Run for Example 1 (National Population
Projection,
Single-Race Model)................................ 159
3. CHECK Run for Example 2 (National Population
Projection,
Two-Race Model)................................... 161
4. PROJ Run for Example 2 (National Population
Projection,
Two-Race Model)................................... 165
5. CHECK Run for Example 3 (State Population
Projection,
Single-Race Model)................................ 168
6. PROJ Run for Example 3 (State Population
Projection,
Single-Race Model)................................ 170
7. CHECK Run for Example 4 (State Population
Projection,
Three-Race, 14-Region Model)...................... 172
8. PROJ Run for Example 4 (State Population
Projection,
Three-Race, 14-Region Model)...................... 180
9. CHECK Run for Example 5 (Projection of the
Hispanic
Population)................................................... 182
10. PROJ Run for Example 5 (Projection of the
Hispanic
Population)................................................... 188
11. CHECK Run for Example 6 (Rehabilitation
Services,
Projection
of the Work-Disabled).............................. 190
12. PROJ Run for Example 6 (Rehabilitation
Services,
Projection
of the Work-Disabled).............................. 193
13. CHECK Run for Example 7 (Projection of School
Enrollment)................................................... 195
14. PROJ Run for Example 7 (Projection of School
Enrollment)................................................... 198
15. CHECK Run for Example 8 (Criminal Justice,
Projection
of
Prison Admissions and Operating Cost)...................... 203
16. PROJ Run for Example 8 (Criminal Justice,
Projection
of
Prison Admissions and Operating Cost)...................... 206
17. CHECK Run for Example 9 (Health Care, Projection
of
the Need
for Short-Term and Long-Term Beds)................... 208
18. PROJ Run for Example 9 (Health Care,
Projection of
the Need
for Short-Term and Long-Term Beds)................... 212
19. CHECK Run for Example 10 (Social Services,
Projection
of Counselors and Budget Needed to
Provide
Social
Services to the Elderly Population).................... 215
20. PROJ Run for Example 10 (Social Services,
Projection
of Counselors and Budget Needed to
Provide
Social
Services to the Elderly Population).................... 219
Listing
1. CHECK Run for Example 1 (National
Population Projection, Single-Race Model)
DESTINY PLANNING AND FORECASTING COMPUTER
PROGRAM PACKAGE, VERSION 1.0
PROGRAM NAME: CHECK
DATE OF RUN (DD/MM/YYYY): 5/ 6/1995
TIME OF RUN (HH:MM:SS):
NAME OF PARAMETER FILE = US801.DAT
GENERAL POPULATION DESCRIPTION:
UNITED STATES RESIDENT POPULATION
BASE YEAR = 1980
NO OF RACIAL/ETHNIC GROUPS = 1
NO OF REGIONS = 0
VITAL STATISTICS PARAMETER OPTION = 1
LIFE TABLE OPTION = 1
EXTERNAL MIGRATION OPTION = 1
INTERNAL MIGRATION OPTION = 0
SERVICE SYSTEM OPTION = 0
NAME(S) OF RACE ...
ALL
PARAMETERS FOR RACE = ALL
TOTAL FERTILITY RATE(S)...
1.810
FERTILITY AGE DISTRIBUTION(S)...
.147 .312 .312 .166 .052 .011
INFANT MORTALITY RATE(S)...
14.80
EXPECTATION OF LIFE AT BIRTH CORRESPONDING TO
IMR FOR FIRST
PROJECTION PERIOD = 73.96
BASE‑YEAR POPULATION AND SURVIVAL
PROBABILITIES FOR FIRST PROJECTION PERIOD...
MALE FEMALE MALE
FEMALE
0 .9793 .9852
0‑4 8360135. 7984272. .9967
.9977
5‑9 8537903. 8159231. .9981
.9989
10‑14 9315055. 8925864. .9974
.9987
15‑19 10751544.
10410123. .9960 .9980
20‑24 10660063.
10652494. .9953 .9973
25‑29 9703259. 9814413. .9951
.9966
30‑34 8675505. 8882452. .9940
.9954
35‑39 6860236. 7102772. .9913
.9933
40‑44 5707550. 5960689. .9857
.9894
45‑49 5387511. 5700872. .9757
.9830
50‑54 5620474. 6088510. .9586
.9731
55‑59 5481152.
6132902. .9321
.9567
60‑64 4669307. 5416404. .8913
.9265
65‑69 3902083. 4878761. .8282
.8727
70‑74 2853116. 3943626. .7358
.7856
75+ 3547402. 6419145. .4891
.5275
TOTAL
110032295. 116472530.
TOTAL BASE‑YEAR POPULATION (POPBASE) =
226504825.
CRUDE BIRTH RATE FOR BASE YEAR = 15.90
CRUDE DEATH RATE FOR BASE YEAR = 8.70
INFANT MORTALITY RATE FOR BASE YEAR = 13.80
POPULATION (POPPREV) TEN YEARS PRIOR TO BASE
YEAR = 203302031.
AVERAGE CRUDE BIRTH RATE FOR PREVIOUS TEN
YEARS = 15.14
AVERAGE CRUDE DEATH RATE FOR PREVIOUS TEN
YEARS = 8.96
AVERAGE INFANT MORTALITY RATE FOR PREVIOUS TEN
YEARS = 16.08
ANNUAL EXTERNAL MIGRATION RATE(S) (PER 1000)
(EMRATE)...
.000
ANNUAL EXTERNAL MIGRATION NUMBER(S) (IMMNO)...
1000075.
TOTAL FERTILITY RATE (TFREST) ESTIMATED FROM
BASE‑YEAR BIRTH RATE = 1.833
TOTAL FERTILITY RATE (TFR) SPECIFIED FOR FIRST
PROJECTION PERIOD = 1.810
GENERAL FERTILITY RATE (BIRTH RATE (BRFF)
PER 1000 FEMALES AGED 15‑44)
FOR BASE YEAR = 68.18
ESTIMATE OF ANNUAL NET EXTERNAL MIGRATION
NUMBER (BASED ON BIRTH RATE
AND DEATH RATE FOR PREVIOUS TEN YEARS)
= 1000075.
ESTIMATED ANNUAL RATE PER 1000 = 4.686
ANNUAL NET MIGRATION NUMBER SPECIFIED FOR
FIRST PROJECTION PERIOD = 1000075.
ANNUAL NET MIGRATION RATE PER 1000 SPECIFIED
FOR FIRST PROJECTION
PERIOD =
.000
ANNUAL NET MIGRATION (MIG) IMPLIED BY MIGRATION
NUMBER (IMMNO) AND/OR
MIGRATION RATE (EMRATE) SPECIFIED FOR FIRST
PROJECTION PERIOD = 1000075.
APPROX ANNUAL RATE PER 1000 POPULATION
(MIGR) = 4.415
CRUDE BIRTH RATE PER 1000 (CBR) FOR FIRST
PROJECTION PERIOD = 14.573
CRUDE DEATH RATE PER 1000 (CDR) FOR FIRST
PROJECTION PERIOD = 9.799
AVERAGE ANNUAL POPULATION GROWTH RATE PER 1000
FOR PREVIOUS TEN YEARS
= 1000((POPBASE/POPPREV(IR))**.1‑1)
= 10.87
PROJECTED POPULATION GROWTH RATE (GIVEN
SPECIFIED PARAMETERS):
1000((POPPROJ/POPBASE)**.2‑1) = 9.62
APPROX. ANNUAL POPULATION GROWTH RATE PER
1000, BASED ON CBR,
CDR, AND MIGR = CBR‑CDR+MIGR = 9.19
Listing
2. PROJ Run for Example 1 (National
Population Projection, Single-Race Model)
DESTINY PLANNING AND FORECASTING COMPUTER
PROGRAM PACKAGE, VERSION 1.0
PROGRAM NAME: PROJ
DATE OF RUN (DD/MM/YYYY): 5/ 6/1995
TIME OF RUN (HH:MM:SS): 11:39: 2
PARAMETER FILE NAME: US801.DAT
GENERAL POPULATION DESCRIPTION:
UNITED STATES RESIDENT POPULATION
BASE YEAR: 1980
NO OF FIVE‑YEAR PERIODS TO PROJECT = 2
YEAR: 1990
DISTRIBUTIONAL ANALYSIS OF POPULATN
TOTAL POPULATN = 250026462.
DISTRIBUTION OF POPULATN
BY AGE
0‑4 18150140.
5‑9 18340630.
10‑14 16961798.
15‑19 17341700.
20‑24 18916165.
25‑29 21907018.
30‑34 22038919.
35‑39 20150596.
40‑44 18063934.
45‑49 14262631.
50‑54 11763287.
55‑59 10935458.
60‑64 11141584.
65‑69 10411490.
70‑74 8156979.
75+
11484134.
DISTRIBUTION OF POPULATN
BY SEX
MALE
122714472.
FEMALE
127311990.
CROSSTABULATION OF POPULATN
BY AGE AND SEX
MALE FEMALE
0‑4
9229281. 8920859.
5‑9 9321578. 9019052.
10‑14 8668490. 8293308.
15‑19 8858743. 8482957.
20‑24 9644578. 9271587.
25‑29 11108700.
10798317.
30‑34 11004406.
11034512.
35‑39 10003094.
10147502.
40‑44 8909808. 9154126.
45‑49 6987165. 7275467.
50‑54 5721375. 6041912.
55‑59 5251952. 5683506.
60‑64 5234019. 5907564.
65‑69 4745989. 5665501.
70‑74 3592512. 4564467.
75+
4432781. 7051353.
Listing
3. CHECK Run for Example 2 (National
Population Projection, Two-Race Model)
DESTINY PLANNING AND FORECASTING COMPUTER
PROGRAM PACKAGE, VERSION 1.0
PROGRAM NAME: CHECK
DATE OF RUN (DD/MM/YYYY): 5/ 6/1995
TIME OF RUN (HH:MM:SS):
NAME OF PARAMETER FILE = US802.DAT
GENERAL POPULATION DESCRIPTION:
UNITED STATES RESIDENT POPULATION BY RACE
(W/O)
BASE YEAR = 1980
NO OF RACIAL/ETHNIC GROUPS = 2
NO OF REGIONS = 0
VITAL STATISTICS PARAMETER OPTION = 1
LIFE TABLE OPTION = 1
EXTERNAL MIGRATION OPTION = 1
INTERNAL MIGRATION OPTION = 0
SERVICE SYSTEM OPTION = 0
NAME(S) OF RACE ...
WHITE
OTHER
PARAMETERS FOR RACE = WHITE
TOTAL FERTILITY RATE(S)...
1.717
FERTILITY AGE DISTRIBUTION(S)...
.130 .312 .326 .170 .051 .011
INFANT MORTALITY RATE(S)...
12.95
EXPECTATION OF LIFE AT BIRTH CORRESPONDING TO
IMR FOR FIRST
PROJECTION PERIOD = 74.67
BASE‑YEAR POPULATION AND SURVIVAL
PROBABILITIES FOR FIRST PROJECTION PERIOD...
MALE FEMALE MALE
FEMALE
0 .9820 .9874
0‑4 6482766. 6148431. .9974
.9982
5‑9 6684406. 6346611. .9984
.9991
10‑14 7407610. 7052673. .9977
.9989
15‑19 8631389. 8326152. .9965
.9983
20‑24 8680290. 8603095. .9959
.9978
25‑29 8004161. 7978484. .9957
.9972
30‑34 7298603. 7344080. .9948
.9961
35‑39 5830238. 5928994. .9923
.9942
40‑44 4849123. 4976012. .9871
.9904
45‑49 4638090. 4817869. .9774 .9843
50‑54 4918050. 5238845. .9609
.9749
55‑59 4852081. 5384727. .9350
.9592
60‑64 4172521. 4801456. .8951
.9298
65‑69 3481097. 4329974. .8327
.8771
70‑74 2551944. 3542234. .7411
.7910
75+ 3187257. 5851527. .4938
.5322
TOTAL
91669626. 96671164.
TOTAL BASE‑YEAR POPULATION (POPBASE) =
188340790.
CRUDE BIRTH RATE FOR BASE YEAR = 14.80
CRUDE DEATH RATE FOR BASE YEAR = 8.80
INFANT MORTALITY RATE FOR BASE YEAR = 12.00
POPULATION (POPPREV) TEN YEARS PRIOR TO BASE
YEAR = 178098000.
AVERAGE CRUDE BIRTH RATE FOR PREVIOUS TEN
YEARS = 14.13
AVERAGE CRUDE DEATH RATE FOR PREVIOUS TEN
YEARS = 9.04
AVERAGE INFANT MORTALITY RATE FOR PREVIOUS TEN
YEARS = 14.11
ANNUAL EXTERNAL MIGRATION RATE(S) (PER 1000)
(EMRATE)...
.000
ANNUAL EXTERNAL MIGRATION NUMBER(S) (IMMNO)...
94517.
TOTAL FERTILITY RATE (TFREST) ESTIMATED FROM
BASE‑YEAR BIRTH RATE = 1.748
TOTAL FERTILITY RATE (TFR) SPECIFIED FOR FIRST
PROJECTION PERIOD = 1.717
GENERAL FERTILITY RATE (BIRTH RATE (BRFF)
PER 1000 FEMALES AGED 15‑44)
FOR BASE YEAR = 64.59
ESTIMATE OF ANNUAL NET EXTERNAL MIGRATION
NUMBER (BASED ON BIRTH RATE
AND DEATH RATE FOR PREVIOUS TEN YEARS)
= 94517.
ESTIMATED ANNUAL RATE PER 1000 = .518
ANNUAL NET MIGRATION NUMBER SPECIFIED FOR
FIRST PROJECTION PERIOD = 94517.
ANNUAL NET MIGRATION RATE PER 1000 SPECIFIED
FOR FIRST PROJECTION
PERIOD
= .000
ANNUAL NET MIGRATION (MIG) IMPLIED BY
MIGRATION NUMBER (IMMNO) AND/OR
MIGRATION RATE (EMRATE) SPECIFIED FOR FIRST
PROJECTION PERIOD = 94517.
APPROX ANNUAL RATE PER 1000 POPULATION
(MIGR) = .502
CRUDE BIRTH RATE PER 1000 (CBR) FOR FIRST
PROJECTION PERIOD = 13.566
CRUDE DEATH RATE PER 1000 (CDR) FOR FIRST
PROJECTION PERIOD = 10.145
AVERAGE ANNUAL POPULATION GROWTH RATE PER 1000
FOR PREVIOUS TEN YEARS
= 1000((POPBASE/POPPREV(IR))**.1‑1)
= 5.61
PROJECTED POPULATION GROWTH RATE (GIVEN
SPECIFIED PARAMETERS):
1000((POPPROJ/POPBASE)**.2‑1) = 4.46
APPROX. ANNUAL POPULATION GROWTH RATE PER
1000, BASED ON CBR,
CDR, AND MIGR = CBR‑CDR+MIGR = 3.92
PARAMETERS FOR RACE = OTHER
TOTAL FERTILITY RATE(S)...
2.334
FERTILITY AGE DISTRIBUTION(S)...
.221 .312 .251 .143 .058 .015
INFANT MORTALITY RATE(S)...
22.62
EXPECTATION OF LIFE AT BIRTH CORRESPONDING TO
IMR FOR FIRST
PROJECTION PERIOD = 70.99
BASE‑YEAR POPULATION AND SURVIVAL
PROBABILITIES FOR FIRST PROJECTION PERIOD...
MALE FEMALE MALE
FEMALE
0 .9675 .9757
0‑4 1877369. 1835841. .9941
.9956
5‑9 1853497.
1812620. .9969 .9979
10‑14 1907445. 1873191. .9961
.9976
15‑19 2120155. 2083971. .9939
.9963
20‑24 1979773. 2049399. .9928
.9952
25‑29 1699098. 1835929. .9923
.9941
30‑34 1376902. 1538372. .9907
.9926
35‑39 1029998. 1173778. .9871
.9898
40‑44 858427. 984677. .9802
.9850
45‑49 749421. 883003. .9683 .9773
50‑54 702424. 849665. .9491
.9655
55‑59 629071. 748175. .9196
.9462
60‑64 496786. 614948. .8756
.9122
65‑69 420986. 548787. .8091
.8541
70‑74 301172. 401392. .7136
.7629
75+ 360145. 567618. .4691
.5074
TOTAL
18362669. 19801366.
TOTAL BASE‑YEAR POPULATION (POPBASE)
= 38164035.
CRUDE BIRTH RATE FOR BASE YEAR = 22.80
CRUDE DEATH RATE FOR BASE YEAR = 7.80
INFANT MORTALITY RATE FOR BASE YEAR = 21.10
POPULATION (POPPREV) TEN YEARS PRIOR TO BASE
YEAR = 25137000.
AVERAGE CRUDE BIRTH RATE FOR PREVIOUS TEN
YEARS = 21.77
AVERAGE CRUDE DEATH RATE FOR PREVIOUS TEN
YEARS = 8.33
AVERAGE INFANT MORTALITY RATE FOR PREVIOUS TEN
YEARS = 24.19
ANNUAL EXTERNAL MIGRATION RATE(S) (PER 1000)
(EMRATE)...
.000
ANNUAL EXTERNAL MIGRATION NUMBER(S) (IMMNO)...
888003.
TOTAL FERTILITY RATE (TFREST) ESTIMATED FROM
BASE‑YEAR BIRTH RATE = 2.335
TOTAL FERTILITY RATE (TFR) SPECIFIED FOR FIRST
PROJECTION PERIOD = 2.334
GENERAL FERTILITY RATE (BIRTH RATE (BRFF)
PER 1000 FEMALES AGED 15‑44)
FOR BASE YEAR = 90.02
ESTIMATE OF ANNUAL NET EXTERNAL MIGRATION
NUMBER (BASED ON BIRTH RATE
AND DEATH RATE FOR PREVIOUS TEN YEARS)
= 888003.
ESTIMATED ANNUAL RATE PER 1000 = 29.199
ANNUAL NET MIGRATION NUMBER SPECIFIED FOR
FIRST PROJECTION PERIOD = 888003.
ANNUAL NET MIGRATION RATE PER 1000 SPECIFIED
FOR FIRST PROJECTION
PERIOD =
.000
ANNUAL NET MIGRATION (MIG) IMPLIED BY
MIGRATION NUMBER (IMMNO) AND/OR
MIGRATION RATE (EMRATE) SPECIFIED FOR FIRST
PROJECTION PERIOD = 888003.
APPROX ANNUAL RATE PER 1000 POPULATION
(MIGR) = 23.268
CRUDE BIRTH RATE PER 1000 (CBR) FOR FIRST
PROJECTION PERIOD = 20.621
CRUDE DEATH RATE PER 1000 (CDR) FOR FIRST
PROJECTION PERIOD = 7.636
AVERAGE ANNUAL POPULATION GROWTH RATE PER 1000
FOR PREVIOUS TEN YEARS
= 1000((POPBASE/POPPREV(IR))**.1‑1)
= 42.64
PROJECTED POPULATION GROWTH RATE (GIVEN
SPECIFIED PARAMETERS):
1000((POPPROJ/POPBASE)**.2‑1) = 34.74
APPROX. ANNUAL POPULATION GROWTH RATE PER
1000, BASED ON CBR,
CDR, AND MIGR = CBR‑CDR+MIGR = 36.25
TOTAL POPULATION (ALL RACES) = 226504825.
ESTIMATE OF ANNUAL NET EXTERNAL MIGRATION
NUMBER (BASED ON BIRTH RATE AND
DEATH RATE FOR PREVIOUS TEN YEARS; TOTAL
FOR ALL RACES IN THE MODEL)
=
939359.
ESTIMATED ANNUAL RATE PER 1000 = 4.402
Listing
4. PROJ Run for Example 2 (National
Population Projection, Two-Race Model)
DESTINY PLANNING AND FORECASTING COMPUTER
PROGRAM PACKAGE, VERSION 1.0
PROGRAM NAME: PROJ
DATE OF RUN (DD/MM/YYYY): 5/ 6/1995
TIME OF RUN (HH:MM:SS): 12:17: 5
PARAMETER FILE NAME: US802.DAT
GENERAL POPULATION DESCRIPTION:
UNITED STATES RESIDENT POPULATION BY RACE
(W/O)
BASE YEAR: 1980
NO OF FIVE‑YEAR PERIODS TO PROJECT = 2
YEAR: 1990
DISTRIBUTIONAL ANALYSIS OF POPULATN
TOTAL POPULATN = 250738546.
DISTRIBUTION OF POPULATN
BY AGE
0‑4 18669617.
5‑9 18806048.
10‑14 17101239.
15‑19 17460667.
20‑24 19000300.
25‑29 21967328.
30‑34 22058888.
35‑39 20138388.
40‑44 18001916.
45‑49 14192279.
50‑54 11705971.
55‑59 10862325.
60‑64 11041520.
65‑69 10298760.
70‑74 8064410.
75+
11368890.
DISTRIBUTION OF POPULATN
BY SEX
MALE
123028940.
FEMALE
127709605.
DISTRIBUTION OF POPULATN
BY RACE
WHITE 197443844.
OTHER
53294702.
CROSSTABULATION OF POPULATN
BY AGE AND SEX
MALE FEMALE
0‑4 9492151. 9177466.
5‑9 9556684. 9249364.
10‑14 8735127. 8366112.
15‑19 8915115. 8545552.
20‑24 9682667. 9317633.
25‑29 11135944.
10831384.
30‑34 11007309.
11051579.
35‑39 9985651.
10152737.
40‑44 8867066. 9134850.
45‑49 6942907. 7249371.
50‑54 5685799. 6020171.
55‑59 5209615. 5652710.
60‑64 5180874. 5860647.
65‑69 4692481. 5606280.
70‑74 3550310. 4514099.
75+
4389239. 6979651.
CROSSTABULATION OF POPULATN
BY AGE AND RACE
WHITE OTHER
0‑4 13386385. 5283232.
5‑9 13621659. 5184390.
10‑14 12648435. 4452804.
15‑19 13055499. 4405168.
20‑24 14468046. 4532254.
25‑29 16941640. 5025688.
30‑34 17251096. 4807792.
35‑39 15930166. 4208222.
40‑44 14547949. 3453967.
45‑49 11604716. 2587563.
50‑54 9575698. 2130273.
55‑59 9022988. 1839336.
60‑64 9362446. 1679074.
65‑69 8906125. 1392635.
70‑74 7060025. 1004385.
75+
10060972. 1307918.
CROSSTABULATION OF POPULATN
BY SEX AND RACE
MALE FEMALE
WHITE
97116269. 100327575.
OTHER
25912671. 27382030.
CROSSTABULATION OF POPULATN
BY AGE, SEX, AND RACE
WHITE
MALE FEMALE
0‑4 6808785. 6577600.
5‑9 6925470. 6696189.
10‑14 6486648. 6161786.
15‑19 6690797. 6364702.
20‑24 7400519. 7067527.
25‑29 8607548. 8334093.
30‑34 8649989. 8601107.
35‑39 7966863. 7963303.
40‑44 7239716. 7308232.
45‑49 5738483. 5866234.
50‑54 4701144. 4874554.
55‑59 4377281. 4645708.
60‑64 4439947. 4922499.
65‑69 4080277. 4825848.
70‑74 3124926. 3935098.
75+
3877875. 6183096.
OTHER
MALE FEMALE
0‑4 2683366. 2599866.
5‑9 2631214. 2553175.
10‑14 2248479. 2204325.
15‑19 2224318. 2180851.
20‑24 2282148. 2250106.
25‑29 2528396. 2497292.
30‑34 2357320. 2450472.
35‑39 2018788. 2189434.
40‑44 1627350. 1826618.
45‑49 1204425. 1383138.
50‑54 984655. 1145617.
55‑59 832334. 1007002.
60‑64 740927. 938147.
65‑69 612203. 780432.
70‑74 425384. 579001.
75+
511364. 796554.
Listing
5. CHECK Run for Example 3 (State
Population Projection, Single-Race Model)
DESTINY PLANNING AND FORECASTING COMPUTER
PROGRAM PACKAGE, VERSION 1.0
PROGRAM NAME: CHECK
DATE OF RUN (DD/MM/YYYY): 5/ 6/1995
TIME OF RUN (HH:MM:SS):
NAME OF PARAMETER FILE = AZ801.DAT
GENERAL POPULATION DESCRIPTION:
BASE YEAR = 1980
NO OF RACIAL/ETHNIC GROUPS = 1
NO OF REGIONS = 0
VITAL STATISTICS PARAMETER OPTION = 1
LIFE TABLE OPTION = 1
EXTERNAL MIGRATION OPTION = 1
INTERNAL MIGRATION OPTION = 0
SERVICE SYSTEM OPTION = 0
NAME(S) OF RACE ...
ALL
PARAMETERS FOR RACE = ALL
TOTAL FERTILITY RATE(S)...
2.129
FERTILITY AGE DISTRIBUTION(S)...
.147 .312 .312 .166 .052 .011
INFANT MORTALITY RATE(S)...
13.56
EXPECTATION OF LIFE AT BIRTH CORRESPONDING TO
IMR FOR FIRST
PROJECTION PERIOD = 74.44
BASE‑YEAR POPULATION AND SURVIVAL
PROBABILITIES FOR FIRST PROJECTION PERIOD...
MALE FEMALE MALE
FEMALE
0 .9811 .9867
0‑4 109075. 104808. .9972
.9981
5‑9 107650. 103417. .9983
.9990
10‑14 111583. 107990. .9976
.9988
15‑19 128283.
123734. .9963
.9982
20‑24 133486. 130297. .9957
.9976
25‑29 119140. 116911. .9955
.9970
30‑34 104855. 102909. .9945
.9959
35‑39 80333. 82540. .9920
.9939
40‑44 66836. 68279. .9866
.9901
45‑49 61538. 63533. .9769
.9839
50‑54 60295. 66454. .9601
.9743
55‑59 61155. 71352. .9340
.9583
60‑64 57682. 66718. .8938
.9287
65‑69 53009. 61835. .8312
.8757
70‑74 39867. 47409. .7393
.7893
75+ 43155. 62087. .4922
.5307
TOTAL 1337942.
1380273.
TOTAL BASE‑YEAR POPULATION (POPBASE)
= 2718215.
CRUDE BIRTH RATE FOR BASE YEAR = 18.40
CRUDE DEATH RATE FOR BASE YEAR = 7.80
INFANT MORTALITY RATE FOR BASE YEAR = 12.40
POPULATION (POPPREV) TEN YEARS PRIOR TO BASE
YEAR = 1770900.
AVERAGE CRUDE BIRTH RATE FOR PREVIOUS TEN
YEARS = 18.32
AVERAGE CRUDE DEATH RATE FOR PREVIOUS TEN
YEARS = 7.71
AVERAGE INFANT MORTALITY RATE FOR PREVIOUS TEN
YEARS = 14.94
ANNUAL EXTERNAL MIGRATION RATE(S) (PER 1000)
(EMRATE)...
.000
ANNUAL EXTERNAL MIGRATION NUMBER(S) (IMMNO)...
71507.
TOTAL FERTILITY RATE (TFREST) ESTIMATED FROM
BASE‑YEAR BIRTH RATE = 2.129
TOTAL FERTILITY RATE (TFR) SPECIFIED FOR FIRST
PROJECTION PERIOD = 2.129
GENERAL FERTILITY RATE (BIRTH RATE (BRFF) PER
1000 FEMALES AGED 15‑44)
FOR BASE YEAR = 80.07
ESTIMATE OF ANNUAL NET EXTERNAL MIGRATION
NUMBER (BASED ON BIRTH RATE
AND DEATH RATE FOR PREVIOUS TEN YEARS)
= 71507.
ESTIMATED ANNUAL RATE PER 1000 = 33.170
ANNUAL NET MIGRATION NUMBER SPECIFIED FOR
FIRST PROJECTION PERIOD = 71507.
ANNUAL NET MIGRATION RATE PER 1000 SPECIFIED
FOR FIRST PROJECTION
PERIOD =
.000
ANNUAL NET MIGRATION (MIG) IMPLIED BY
MIGRATION NUMBER (IMMNO) AND/OR
MIGRATION RATE (EMRATE) SPECIFIED FOR FIRST
PROJECTION PERIOD = 71507.
APPROX ANNUAL RATE PER 1000 POPULATION
(MIGR) = 26.307
CRUDE BIRTH RATE PER 1000 (CBR) FOR FIRST
PROJECTION PERIOD = 16.896
CRUDE DEATH RATE PER 1000 (CDR) FOR FIRST
PROJECTION PERIOD = 9.272
AVERAGE ANNUAL POPULATION GROWTH RATE PER 1000
FOR PREVIOUS TEN YEARS
= 1000((POPBASE/POPPREV(IR))**.1‑1)
= 43.78
PROJECTED POPULATION GROWTH RATE (GIVEN
SPECIFIED PARAMETERS):
1000((POPPROJ/POPBASE)**.2‑1) = 32.50
APPROX. ANNUAL POPULATION GROWTH RATE PER
1000, BASED ON CBR,
CDR, AND MIGR = CBR‑CDR+MIGR = 33.93
Listing
6. PROJ Run for Example 3 (State
Population Projection, Single-Race Model)
DESTINY PLANNING AND FORECASTING COMPUTER
PROGRAM PACKAGE, VERSION 1.0
PROGRAM NAME: PROJ
DATE OF RUN (DD/MM/YYYY): 5/ 6/1995
TIME OF RUN (HH:MM:SS):
PARAMETER FILE NAME: AZ801.DAT
GENERAL POPULATION DESCRIPTION:
BASE YEAR: 1980
NO OF FIVE‑YEAR PERIODS TO PROJECT = 2
YEAR: 1990
DISTRIBUTIONAL ANALYSIS OF POPULATN
TOTAL POPULATN = 3694625.
DISTRIBUTION OF POPULATN
BY AGE
0‑4 308528.
5‑9 309834.
10‑14 265533.
15‑19 262196.
20‑24 272382.
25‑29 312138.
30‑34 326384.
35‑39 291639.
40‑44 255842.
45‑49 199194.
50‑54 163155.
55‑59 147819.
60‑64 144704.
65‑69 142762.
70‑74 121020.
75+
171493.
DISTRIBUTION OF POPULATN
BY SEX
MALE
1827212.
FEMALE
1867413.
CROSSTABULATION OF POPULATN
BY AGE AND SEX
MALE FEMALE
0‑4 156914. 151614.
5‑9 157507. 152327.
10‑14 135307. 130226.
15‑19 133601. 128596.
20‑24 138207. 134175.
25‑29 158591. 153548.
30‑34 164894. 161490.
35‑39 146991. 144649.
40‑44 128908. 126934.
45‑49 97980. 101214.
50‑54
80273. 82882.
55‑59 71925. 75893.
60‑64 67382. 77322.
65‑69 63623. 79139.
70‑74 53404. 67616.
75+
71705. 99788.
Listing
7. CHECK Run for Example 4 (State Population
Projection, Three-Race, 14-Region Model)
DESTINY PLANNING AND FORECASTING COMPUTER
PROGRAM PACKAGE, VERSION 1.0
PROGRAM NAME: CHECK
DATE OF RUN (DD/MM/YYYY): 5/ 6/1995
TIME OF RUN (HH:MM:SS): 12:52: 1
NAME OF PARAMETER FILE = AZ803C.DAT
GENERAL POPULATION DESCRIPTION:
BASE YEAR = 1980
NO OF RACIAL/ETHNIC GROUPS = 3
NO OF REGIONS = 14
VITAL STATISTICS PARAMETER OPTION = 1
LIFE TABLE OPTION = 1
EXTERNAL MIGRATION OPTION = 1
INTERNAL MIGRATION OPTION = 1
SERVICE SYSTEM OPTION = 0
NAME(S) OF RACE ...
WHITE
AMERIND
OTHER
NAME(S) OF REGION ...
APACHE
COCHISE
COCONINO
GILA
GRAHAM
GREENLEE
MARICOPA
MOHAVE
NAVAJO
PIMA
PINAL
STA.CRUZ
YAVAPAI
PARAMETERS FOR RACE = WHITE
TOTAL FERTILITY RATE(S)...
2.232
FERTILITY AGE DISTRIBUTION(S)...
.130 .312 .326 .170 .051 .011
INFANT MORTALITY RATE(S)...
11.70
EXPECTATION OF LIFE AT BIRTH CORRESPONDING TO
IMR FOR FIRST
PROJECTION PERIOD = 75.14
BASE‑YEAR POPULATION AND SURVIVAL
PROBABILITIES FOR FIRST PROJECTION PERIOD...
MALE
FEMALE MALE FEMALE
0 .9839 .9889
0‑4 79351. 76208. .9978
.9986
5‑9 80415. 76578. .9986
.9992
10‑14 85306. 82032. .9979
.9991
15‑19 99026. 95899. .9968
.9986
20‑24 106315. 104137. .9963
.9981
25‑29 96311. 95364. .9962
.9975
30‑34 87382. 85981. .9953
.9966
35‑39 68203. 69718. .9930
.9947
40‑44 56493. 57394. .9880
.9911
45‑49 52916. 54059. .9786
.9852
50‑54 53052. 58170. .9624
.9761
55‑59 55155. 64721. .9370
.9608
60‑64 53162. 61749. .8976
.9321
65‑69 49283. 57527. .8357
.8801
70‑74 37022. 44379. .7446
.7947
75+ 39590. 57863. .4970
.5354
TOTAL 1098982. 1141779.
TOTAL BASE‑YEAR POPULATION (POPBASE)
= 2240761.
CRUDE BIRTH RATE FOR BASE YEAR = 18.90
CRUDE DEATH RATE FOR BASE YEAR = 8.80
INFANT MORTALITY RATE FOR BASE YEAR = 11.70
POPULATION (POPPREV) TEN YEARS PRIOR TO BASE
YEAR = 1604948.
AVERAGE CRUDE BIRTH RATE FOR PREVIOUS TEN
YEARS = 18.90
AVERAGE CRUDE DEATH RATE FOR PREVIOUS TEN
YEARS = 8.80
AVERAGE INFANT MORTALITY RATE FOR PREVIOUS TEN
YEARS = 11.70
ANNUAL EXTERNAL MIGRATION RATE(S) (PER 1000)
(EMRATE)...
.000
ANNUAL EXTERNAL MIGRATION NUMBER(S) (IMMNO)...
44535.
POPULATION BY REGION...
BASE YEAR TEN YEARS PRIOR
APACHE 11902. 7525.
COCHISE 73261. 59027.
COCONINO 49235. 34141.
GILA 30147. 25662.
GRAHAM 17085. 14201.
GREENLEE 9357. 9793.
MARICOPA 1307455.
914610.
MOHAVE 53477. 24738.
NAVAJO
32543. 26893.
PIMA 442888. 326416.
PINAL 61849. 58141.
STA.CRUZ 16515. 13091.
YAVAPAI 65322. 35713.
TOTAL 2240761. 1604948.
TOTAL FERTILITY RATE (TFREST) ESTIMATED FROM
BASE‑YEAR BIRTH RATE = 2.232
TOTAL FERTILITY RATE (TFR) SPECIFIED FOR FIRST
PROJECTION PERIOD = 2.232
GENERAL FERTILITY RATE (BIRTH RATE (BRFF)
PER 1000 FEMALES AGED 15‑44)
FOR BASE YEAR = 83.29
ESTIMATE OF ANNUAL NET EXTERNAL MIGRATION
NUMBER (BASED ON BIRTH RATE
AND DEATH RATE FOR PREVIOUS TEN YEARS)
= 44535.
ESTIMATED ANNUAL RATE PER 1000 = 23.836
ANNUAL NET MIGRATION NUMBER SPECIFIED FOR
FIRST PROJECTION PERIOD = 44535.
ANNUAL NET MIGRATION RATE PER 1000 SPECIFIED
FOR FIRST PROJECTION
PERIOD =
.000
ANNUAL NET MIGRATION (MIG) IMPLIED BY
MIGRATION NUMBER (IMMNO) AND/OR
MIGRATION RATE (EMRATE) SPECIFIED FOR FIRST
PROJECTION PERIOD = 44535.
APPROX ANNUAL RATE PER 1000 POPULATION
(MIGR) = 19.875
ESTIMATES (BY REGION) OF THE ANNUAL INTERNAL
MIGRATION NUMBER AND RATE (PER
1000) BASED ON THE EXTERNAL MIGRATION
ESTIMATE:
RATE
AMOUNT APPROX
EXACT
APACHE
: 106. 8.874
11.257
COCHISE :
‑692. ‑9.450 ‑10.599
COCONINO:
119. 2.411 2.920
GILA
: ‑430. ‑14.259 ‑15.539
GRAHAM
: ‑207. ‑12.143 ‑13.399
GREENLEE:
‑327. ‑34.897 ‑34.043
MARICOPA:
2309. 1.766 2.130
MOHAVE
: 1433. 26.796
39.480
NAVAJO
: ‑379. ‑11.634 ‑12.877
PIMA
: ‑972. ‑2.194
‑2.576
PINAL
: ‑1462. ‑23.642 ‑24.442
STA.CRUZ:
‑133. ‑8.073 ‑9.132
YAVAPAI :
1170. 17.909 24.387
TOTAL
: 0.
SPECIFIED AND IMPLIED VALUES (BY REGION) OF
THE ANNUAL INTERNAL MIGRATION
NUMBER AND RATE (PER 1000):
SPECIFIED IMPLIED
AMOUNT RATE
AMOUNT RATE
APACHE
: 106. .000
106. 8.906
COCHISE : 0. ‑10.599 ‑776. ‑10.599
COCONINO:
119. .000 119.
2.417
GILA
: 0. ‑15.539 ‑468. ‑15.539
GRAHAM
: 0. ‑13.399 ‑229. ‑13.399
GREENLEE: 0. ‑34.043 ‑319. ‑34.043
MARICOPA:
2309. .000 2309.
1.766
MOHAVE
: 1433. .000
1433. 26.797
NAVAJO
: 0. ‑12.877 ‑419. ‑12.877
PIMA
: 0. ‑2.576 ‑1141. ‑2.576
PINAL
: 0. ‑24.442 ‑1512. ‑24.442
STA.CRUZ: 0.
‑9.132 ‑151. ‑9.132
YAVAPAI :
1170. .000 1170.
17.911
CRUDE BIRTH RATE PER 1000 (CBR) FOR FIRST
PROJECTION PERIOD = 17.463
CRUDE DEATH RATE PER 1000 (CDR) FOR FIRST
PROJECTION PERIOD = 9.938
AVERAGE ANNUAL POPULATION GROWTH RATE PER 1000
FOR PREVIOUS TEN YEARS
= 1000((POPBASE/POPPREV(IR))**.1‑1)
= 33.94
PROJECTED POPULATION GROWTH RATE (GIVEN
SPECIFIED PARAMETERS):
1000((POPPROJ/POPBASE)**.2‑1) = 26.75
APPROX. ANNUAL POPULATION GROWTH RATE PER
1000, BASED ON CBR,
CDR, AND MIGR = CBR‑CDR+MIGR = 27.40
PARAMETERS FOR RACE = AMERIND
TOTAL FERTILITY RATE(S)...
3.487
FERTILITY AGE DISTRIBUTION(S)...
.221 .312 .251 .143 .058 .015
INFANT MORTALITY RATE(S)...
16.20
EXPECTATION OF LIFE AT BIRTH CORRESPONDING TO
IMR FOR FIRST
PROJECTION PERIOD = 73.43
BASE‑YEAR POPULATION AND SURVIVAL
PROBABILITIES FOR FIRST PROJECTION PERIOD...
MALE FEMALE MALE
FEMALE
0 .9772
.9835
0‑4 9853. 9732. .9963
.9973
5‑9 9288. 9237. .9979
.9987
10‑14 9575. 9465. .9972
.9985
15‑19 9931. 9973. .9956
.9977
20‑24 7250. 7979. .9949
.9969
25‑29 5681. 6237. .9946
.9961
30‑34 4817. 4988. .9934
.9949
35‑39 3524. 4054. .9906
.9927
40‑44 3120. 3522. .9848
.9886
45‑49 2532. 3103. .9744
.9820
50‑54 2123. 2579. .9569
.9717
55‑59 1758. 2122. .9298
.9548
60‑64 1362. 1555. .8885
.9239
65‑69 1154. 1382. .8248
.8694
70‑74 928. 916. .7318
.7816
75+ 1349. 1409. .4855
.5239
TOTAL 74245. 78253.
TOTAL BASE‑YEAR POPULATION (POPBASE)
= 152498.
CRUDE BIRTH RATE FOR BASE YEAR = 33.20
CRUDE DEATH RATE FOR BASE YEAR = 6.50
INFANT MORTALITY RATE FOR BASE YEAR = 16.20
POPULATION (POPPREV) TEN YEARS PRIOR TO BASE
YEAR = 95812.
AVERAGE CRUDE BIRTH RATE FOR PREVIOUS TEN
YEARS = 33.20
AVERAGE CRUDE DEATH RATE FOR PREVIOUS TEN
YEARS = 6.50
AVERAGE INFANT MORTALITY RATE FOR PREVIOUS TEN
YEARS = 16.20
ANNUAL EXTERNAL MIGRATION RATE(S) (PER 1000)
(EMRATE)...
.000
ANNUAL EXTERNAL MIGRATION NUMBER(S) (IMMNO)...
2462.
POPULATION BY REGION...
BASE YEAR TEN YEARS PRIOR
APACHE 39024. 24518.
COCHISE 489. 307.
COCONINO 20904. 13134.
GILA
5083. 3194.
GRAHAM 2740. 1721.
GREENLEE 229. 144.
MARICOPA 22788. 14317.
MOHAVE 1462. 919.
NAVAJO 32122. 20182.
PIMA 14880. 9349.
PINAL 8487. 5332.
STA.CRUZ 57. 36.
YAVAPAI 997. 626.
YUMA 3236. 2033.
TOTAL 152498. 95812.
TOTAL FERTILITY RATE (TFREST) ESTIMATED FROM
BASE‑YEAR BIRTH RATE = 3.487
TOTAL FERTILITY RATE (TFR) SPECIFIED FOR FIRST
PROJECTION PERIOD = 3.487
GENERAL FERTILITY RATE (BIRTH RATE (BRFF)
PER 1000 FEMALES AGED 15‑44)
FOR BASE YEAR = 137.76
ESTIMATE OF ANNUAL NET EXTERNAL MIGRATION
NUMBER (BASED ON BIRTH RATE
AND DEATH RATE FOR PREVIOUS TEN YEARS)
= 2462.
ESTIMATED ANNUAL RATE PER 1000 = 20.873
ANNUAL NET MIGRATION NUMBER SPECIFIED FOR
FIRST PROJECTION PERIOD = 2462.
ANNUAL NET MIGRATION RATE PER 1000 SPECIFIED
FOR FIRST PROJECTION
PERIOD =
.000
ANNUAL NET MIGRATION (MIG) IMPLIED BY
MIGRATION NUMBER (IMMNO) AND/OR
MIGRATION RATE (EMRATE) SPECIFIED FOR FIRST
PROJECTION PERIOD = 2462.
APPROX ANNUAL RATE PER 1000 POPULATION
(MIGR) = 16.144
ESTIMATES (BY REGION) OF THE ANNUAL INTERNAL
MIGRATION NUMBER AND RATE (PER
1000) BASED ON THE EXTERNAL MIGRATION
ESTIMATE:
RATE
AMOUNT APPROX
EXACT
APACHE
: 0. .000
.001
COCHISE : 0.
.054 .070
COCONINO: 0.
‑.002 ‑.003
GILA
: 0. ‑.010
‑.013
GRAHAM
: 0. .021
.027
GREENLEE: 0.
‑.062 ‑.079
MARICOPA: 0.
.002 .002
MOHAVE
: 0. ‑.035
‑.045
NAVAJO
: 0. ‑.001
‑.001
PIMA
: 0. ‑.001
‑.001
PINAL
: 0. .003
.004
STA.CRUZ: 0.
‑.380 ‑.486
YAVAPAI : 0.
.046 .059
TOTAL
: 0.
SPECIFIED AND IMPLIED VALUES (BY REGION) OF
THE ANNUAL INTERNAL MIGRATION
NUMBER AND RATE (PER 1000):
SPECIFIED IMPLIED
AMOUNT RATE
AMOUNT RATE
APACHE
: 0. .000
0. .000
COCHISE : 0.
.000 0. .000
COCONINO: 0.
.000 0. .000
GILA
: 0. .000
0. .000
GRAHAM
: 0. .000
0. .000
GREENLEE: 0.
.000 0. .000
MARICOPA: 0.
.000 0. .000
MOHAVE
: 0. .000
0. .000
NAVAJO
: 0. .000
0. .000
PIMA
: 0. .000
0. .000
PINAL
: 0. .000
0. .000
STA.CRUZ: 0.
.000 0. .000
YAVAPAI : 0.
.000 0. .000
YUMA
: 0. .000
0. .000
CRUDE BIRTH RATE PER 1000 (CBR) FOR FIRST
PROJECTION PERIOD = 28.208
CRUDE DEATH RATE PER 1000 (CDR) FOR FIRST
PROJECTION PERIOD = 5.230
AVERAGE ANNUAL POPULATION GROWTH RATE PER 1000
FOR PREVIOUS TEN YEARS
= 1000((POPBASE/POPPREV(IR))**.1‑1)
= 47.57
PROJECTED POPULATION GROWTH RATE (GIVEN
SPECIFIED PARAMETERS):
1000((POPPROJ/POPBASE)**.2‑1) = 37.84
APPROX. ANNUAL POPULATION GROWTH RATE PER
1000, BASED ON CBR,
CDR, AND MIGR = CBR‑CDR+MIGR = 39.12
PARAMETERS FOR RACE = OTHER
TOTAL FERTILITY RATE(S)...
2.346
FERTILITY AGE DISTRIBUTION(S)...
.221 .312 .251 .143 .058 .015
INFANT MORTALITY RATE(S)...
21.10
EXPECTATION OF LIFE AT BIRTH CORRESPONDING TO IMR
FOR FIRST
PROJECTION PERIOD = 71.57
BASE‑YEAR POPULATION AND SURVIVAL
PROBABILITIES FOR FIRST PROJECTION PERIOD...
MALE FEMALE MALE
FEMALE
0 .9698 .9775
0‑4 19871. 18868. .9946
.9960
5‑9 17947. 17602. .9971
.9981
10‑14 16702. 16493. .9963
.9978
15‑19 19326. 17862. .9943
.9966
20‑24 19921. 18181. .9933
.9956
25‑29 17148. 15310. .9929
.9946
30‑34 12656. 11940. .9913
.9931
35‑39 8606. 8768. .9879
.9905
40‑44 7223. 7363. .9813
.9859
45‑49 6090. 6371. .9697
.9784
50‑54 5120. 5705. .9509
.9670
55‑59 4242. 4509. .9220
.9482
60‑64 3158. 3414. .8787
.9150
65‑69 2572. 2926. .8128
.8577
70‑74 1917. 2114. .7179
.7673
75+ 2216. 2815. .4730
.5113
TOTAL 164715. 160241.
TOTAL BASE‑YEAR POPULATION (POPBASE)
= 324956.
CRUDE BIRTH RATE FOR BASE YEAR = 22.80
CRUDE DEATH RATE FOR BASE YEAR = 7.80
INFANT MORTALITY RATE FOR BASE YEAR = 21.10
POPULATION (POPPREV) TEN YEARS PRIOR TO BASE
YEAR = 70140.
AVERAGE CRUDE BIRTH RATE FOR PREVIOUS TEN
YEARS = 22.80
AVERAGE CRUDE DEATH RATE FOR PREVIOUS TEN
YEARS = 7.80
AVERAGE INFANT MORTALITY RATE FOR PREVIOUS TEN
YEARS = 21.10
ANNUAL EXTERNAL MIGRATION RATE(S) (PER 1000)
(EMRATE)...
.000
ANNUAL EXTERNAL MIGRATION NUMBER(S) (IMMNO)...
22756.
POPULATION BY REGION...
BASE YEAR TEN YEARS PRIOR
APACHE 1182. 255.
COCHISE 11936. 2576.
COCONINO 4869. 1051.
GILA 1850. 399.
GRAHAM 3037.
656.
GREENLEE 1820. 393.
MARICOPA 178809. 38595.
MOHAVE 926. 200.
NAVAJO 2964. 640.
PIMA 73675. 15902.
PINAL 20582. 4443.
STA.CRUZ 3887. 839.
YAVAPAI 1826. 394.
YUMA 17593. 3797.
TOTAL 324956. 70140.
TOTAL FERTILITY RATE (TFREST) ESTIMATED FROM
BASE‑YEAR BIRTH RATE = 2.346
TOTAL FERTILITY RATE (TFR) SPECIFIED FOR FIRST
PROJECTION PERIOD = 2.346
GENERAL FERTILITY RATE (BIRTH RATE (BRFF)
PER 1000 FEMALES AGED 15‑44)
FOR BASE YEAR = 93.28
ESTIMATE OF ANNUAL NET EXTERNAL MIGRATION
NUMBER (BASED ON BIRTH RATE
AND DEATH RATE FOR PREVIOUS TEN YEARS)
= 22756.
ESTIMATED ANNUAL RATE PER 1000 = 150.698
ANNUAL NET MIGRATION NUMBER SPECIFIED FOR
FIRST PROJECTION PERIOD = 22756.
ANNUAL NET MIGRATION RATE PER 1000 SPECIFIED
FOR FIRST PROJECTION
PERIOD =
.000
ANNUAL NET MIGRATION (MIG) IMPLIED BY
MIGRATION NUMBER (IMMNO) AND/OR
MIGRATION RATE (EMRATE) SPECIFIED FOR FIRST
PROJECTION PERIOD = 22756.
APPROX ANNUAL RATE PER 1000 POPULATION
(MIGR) = 70.028
ESTIMATES (BY REGION) OF THE ANNUAL INTERNAL
MIGRATION NUMBER AND RATE (PER
1000)
BASED ON THE EXTERNAL MIGRATION ESTIMATE:
RATE
AMOUNT APPROX
EXACT
APACHE
: 0. .012
.021
COCHISE : 0.
.003 .005
COCONINO: 0.
‑.001 ‑.002
GILA
: 0. .018
.033
GRAHAM
: 0. ‑.017
‑.031
GREENLEE: 0.
‑.010 ‑.018
MARICOPA: 0.
.000 .000
MOHAVE
: 0. ‑.015
‑.027
NAVAJO
: 0. ‑.009
‑.016
PIMA
: 0. .001
.001
PINAL
: 0. ‑.003
‑.005
STA.CRUZ: 0.
.000 ‑.001
YAVAPAI : 0.
.008 .014
YUMA
: 0. .002
.004
TOTAL
: 0.
SPECIFIED AND IMPLIED VALUES (BY REGION) OF
THE ANNUAL INTERNAL MIGRATION
NUMBER AND RATE (PER 1000):
SPECIFIED IMPLIED
AMOUNT RATE
AMOUNT RATE
APACHE
: 0. .000
0. .000
COCHISE : 0.
.000 0. .000
COCONINO: 0.
.000 0. .000
GILA
: 0. .000
0. .000
GRAHAM
: 0. .000
0. .000
GREENLEE: 0.
.000 0. .000
MARICOPA: 0.
.000 0. .000
MOHAVE
: 0. .000
0. .000
NAVAJO
: 0. .000
0. .000
PIMA
: 0. .000
0. .000
PINAL
: 0. .000
0. .000
STA.CRUZ: 0.
.000 0. .000
YAVAPAI : 0.
.000 0. .000
YUMA
: 0. .000
0. .000
CRUDE BIRTH RATE PER 1000 (CBR) FOR FIRST
PROJECTION PERIOD = 20.349
CRUDE DEATH RATE PER 1000 (CDR) FOR FIRST
PROJECTION PERIOD = 5.571
AVERAGE ANNUAL POPULATION GROWTH RATE PER 1000
FOR PREVIOUS TEN YEARS
= 1000((POPBASE/POPPREV(IR))**.1‑1) =
165.70
PROJECTED POPULATION GROWTH RATE (GIVEN
SPECIFIED PARAMETERS):
1000((POPPROJ/POPBASE)**.2‑1) = 73.94
APPROX. ANNUAL POPULATION GROWTH RATE PER
1000, BASED ON CBR,
CDR, AND MIGR = CBR‑CDR+MIGR = 84.81
TOTAL POPULATION (ALL RACES) = 2718215.
ESTIMATE OF ANNUAL NET EXTERNAL MIGRATION
NUMBER (BASED ON BIRTH RATE AND
DEATH RATE FOR PREVIOUS TEN YEARS; TOTAL
FOR ALL RACES IN THE MODEL)
=
69311.
ESTIMATED ANNUAL RATE PER 1000 = 32.163
Listing
8. PROJ Run for Example 4 (State Population
Projection, Three-Race, 14-Region Model)
DESTINY PLANNING AND FORECASTING COMPUTER
PROGRAM PACKAGE, VERSION 1.0
PROGRAM NAME: PROJ
DATE OF RUN (DD/MM/YYYY): 5/ 6/1995
TIME OF RUN (HH:MM:SS): 12:53:32
PARAMETER FILE NAME: AZ803C.DAT
GENERAL POPULATION DESCRIPTION:
BASE YEAR: 1980
NO OF FIVE‑YEAR PERIODS TO PROJECT = 2
YEAR: 1990
DISTRIBUTIONAL ANALYSIS OF POPULATN
TOTAL POPULATN = 3735219.
DISTRIBUTION OF POPULATN
BY RACE
WHITE
2886323.
AMERIND
228240.
OTHER
620656.
DISTRIBUTION OF POPULATN
BY REGION
APACHE
72497.
COCHISE
97683.
COCONINO
97171.
GILA
40759.
GRAHAM
26383.
GREENLEE
11039.
MARICOPA
1893992.
MOHAVE
83827.
NAVAJO
84127.
PIMA
649633.
PINAL
101590.
STA.CRUZ
24075.
YAVAPAI
95609.
YUMA
108068.
CROSSTABULATION OF POPULATN
BY REGION AND RACE
WHITE AMERIND OTHER
APACHE
15397. 55256. 1844.
COCHISE
78373. 692. 18618.
COCONINO
59977. 29599. 7595.
GILA
30676. 7197. 2886.
GRAHAM
17766. 3880. 4737.
GREENLEE
7876. 324. 2839.
MARICOPA
1582814. 32267. 278911.
MOHAVE
80313. 2070. 1444.
NAVAJO
34020. 45483. 4623.
PIMA
513643. 21069. 114920.
PINAL 57469. 12017. 32104.
STA.CRUZ
17931. 81. 6063.
YAVAPAI
91349. 1412. 2848.
YUMA
76044. 4582. 27442.
Listing
9. CHECK Run for Example 5
(Projection of the Hispanic Population)
DESTINY PLANNING AND FORECASTING COMPUTER
PROGRAM PACKAGE, VERSION 1.0
PROGRAM NAME: CHECK
DATE OF RUN (DD/MM/YYYY): 5/ 6/1995
TIME OF RUN (HH:MM:SS): 12:59:28
NAME OF PARAMETER FILE = AZ80HC.DAT
GENERAL POPULATION DESCRIPTION:
BASE YEAR = 1980
NO OF RACIAL/ETHNIC GROUPS = 2
NO OF REGIONS = 14
VITAL STATISTICS PARAMETER OPTION = 1
LIFE TABLE OPTION = 1
EXTERNAL MIGRATION OPTION = 1
INTERNAL MIGRATION OPTION = 1
SERVICE SYSTEM OPTION = 0
NAME(S) OF RACE ...
HISPANIC
NON HISP
NAME(S) OF REGION ...
APACHE
COCHISE
COCONINO
GILA
GRAHAM
GREENLEE
MARICOPA
MOHAVE
NAVAJO
PIMA
PINAL
STA.CRUZ
YAVAPAI
YUMA
PARAMETERS FOR RACE = HISPANIC
TOTAL FERTILITY RATE(S)...
3.190
FERTILITY AGE DISTRIBUTION(S)...
.221 .312 .251 .143 .058 .015
INFANT MORTALITY RATE(S)...
12.40
EXPECTATION OF LIFE AT BIRTH CORRESPONDING TO
IMR FOR FIRST
PROJECTION PERIOD = 74.88
BASE‑YEAR POPULATION AND SURVIVAL
PROBABILITIES FOR FIRST PROJECTION PERIOD...
MALE FEMALE MALE
FEMALE
0 .9829 .9881
0‑4 27940. 26823. .9976
.9984
5‑9 25652. 25079. .9985
.9991
10‑14 24234. 23538. .9978
.9990
15‑19 26081. 24824. .9966
.9985
20‑24 23080. 22734. .9961
.9979
25‑29 20171. 19195. .9959
.9973
30‑34 15889. 15780. .9950
.9963
35‑39 11668. 12241. .9926
.9944
40‑44 9644. 10217. .9875
.9907
45‑49 8380. 9015. .9780
.9847
50‑54 7608. 8290. .9616
.9754
55‑59 6317. 6759. .9359
.9599
60‑64 4672. 5073. .8962
.9309
65‑69 3525. 3986. .8340
.8784
70‑74 2545. 2938. .7427
.7926
75+ 2840. 3963. .4952
.5337
TOTAL 220246. 220455.
TOTAL BASE‑YEAR POPULATION (POPBASE)
= 440701.
CRUDE BIRTH RATE FOR BASE YEAR = 29.70
CRUDE DEATH RATE FOR BASE YEAR = 7.80
INFANT MORTALITY RATE FOR BASE YEAR = 12.40
POPULATION (POPPREV) TEN YEARS PRIOR TO BASE
YEAR = 293485.
AVERAGE CRUDE BIRTH RATE FOR PREVIOUS TEN
YEARS = 29.70
AVERAGE CRUDE DEATH RATE FOR PREVIOUS TEN
YEARS = 7.80
AVERAGE INFANT MORTALITY RATE FOR PREVIOUS TEN
YEARS = 12.40
ANNUAL EXTERNAL MIGRATION RATE(S) (PER 1000)
(EMRATE)...
.000
ANNUAL EXTERNAL MIGRATION NUMBER(S) (IMMNO)...
8159.
POPULATION BY REGION...
BASE YEAR TEN YEARS PRIOR
APACHE 1983. 1229.
COCHISE 22846. 16507.
COCONINO 7315. 4713.
GILA 7723. 6093.
GRAHAM 5457. 3957.
GREENLEE 5446. 4932.
MARICOPA 199003.
127590.
MOHAVE 2148. 994.
NAVAJO 4538. 3202.
PIMA 111418. 73728.
PINAL 26752. 19984.
STA.CRUZ 15229. 10396.
YAVAPAI 4205. 2267.
YUMA 26638. 17893.
TOTAL 440701. 293485.
TOTAL FERTILITY RATE (TFREST) ESTIMATED FROM
BASE‑YEAR BIRTH RATE = 3.190
TOTAL FERTILITY RATE (TFR) SPECIFIED FOR FIRST
PROJECTION PERIOD = 3.190
GENERAL FERTILITY RATE (BIRTH RATE (BRFF)
PER 1000 FEMALES AGED 15‑44)
FOR BASE YEAR = 124.67
ESTIMATE OF ANNUAL NET EXTERNAL MIGRATION
NUMBER (BASED ON BIRTH RATE
AND DEATH RATE FOR PREVIOUS TEN YEARS)
= 6901.
ESTIMATED ANNUAL RATE PER 1000 = 19.592
ANNUAL NET MIGRATION NUMBER SPECIFIED FOR
FIRST PROJECTION PERIOD = 8159.
ANNUAL NET MIGRATION RATE PER 1000 SPECIFIED
FOR FIRST PROJECTION
PERIOD =
.000
ANNUAL NET MIGRATION (MIG) IMPLIED BY
MIGRATION NUMBER (IMMNO) AND/OR
MIGRATION RATE (EMRATE) SPECIFIED FOR FIRST
PROJECTION PERIOD = 8159.
APPROX ANNUAL RATE PER 1000 POPULATION
(MIGR) = 18.514
ESTIMATES (BY REGION) OF THE ANNUAL INTERNAL
MIGRATION NUMBER AND RATE (PER
1000) BASED ON THE EXTERNAL MIGRATION
ESTIMATE:
RATE
AMOUNT APPROX
EXACT
APACHE
: 10. 5.193
6.697
COCHISE :
‑145. ‑6.362 ‑7.581
COCONINO:
18. 2.435 3.079
GILA
: ‑107. ‑13.829 ‑15.731
GRAHAM
: ‑36. ‑6.653
‑7.913
GREENLEE:
‑147. ‑26.947 ‑28.458
MARICOPA:
555. 2.789 3.535
MOHAVE
: 49. 22.846
34.036
NAVAJO
: ‑20. ‑4.458
‑5.378
PIMA
: 53. .475
.593
PINAL
: ‑244. ‑9.114 ‑10.672
STA.CRUZ:
‑29. ‑1.877 ‑2.304
YAVAPAI :
60. 14.260 19.723
YUMA
: ‑17. ‑.648
‑.801
TOTAL
: 0.
SPECIFIED AND IMPLIED VALUES (BY REGION) OF THE
ANNUAL INTERNAL MIGRATION
NUMBER AND RATE (PER 1000):
SPECIFIED IMPLIED
AMOUNT RATE
AMOUNT RATE
APACHE
: 10. .000
10. 5.043
COCHISE : 0.
‑7.581 ‑173. ‑7.581
COCONINO:
18. .000 18.
2.461
GILA
: 0. ‑15.731 ‑121. ‑15.731
GRAHAM
: 0. ‑7.913 ‑43. ‑7.913
GREENLEE: 0. ‑28.458 ‑155. ‑28.458
MARICOPA:
555. .000 555.
2.789
MOHAVE
: 49. .000
49. 22.812
NAVAJO
: 0. ‑5.378 ‑24. ‑5.378
PIMA
: 53. .000
53. .476
PINAL
: 0. ‑10.672 ‑285. ‑10.672
STA.CRUZ: 0.
‑2.304 ‑35. ‑2.304
YAVAPAI :
60. .000 60.
14.269
YUMA
: 0. ‑.801 ‑21. ‑.801
CRUDE BIRTH RATE PER 1000 (CBR) FOR FIRST
PROJECTION PERIOD = 26.087
CRUDE DEATH RATE PER 1000 (CDR) FOR FIRST
PROJECTION PERIOD = 4.570
AVERAGE ANNUAL POPULATION GROWTH RATE PER 1000
FOR PREVIOUS TEN YEARS
= 1000((POPBASE/POPPREV(IR))**.1‑1)
= 41.49
PROJECTED POPULATION GROWTH RATE (GIVEN
SPECIFIED PARAMETERS):
1000((POPPROJ/POPBASE)**.2‑1) = 38.40
APPROX. ANNUAL POPULATION GROWTH RATE PER
1000, BASED ON CBR,
CDR, AND MIGR = CBR‑CDR+MIGR = 40.03
PARAMETERS FOR RACE = NON HISP
TOTAL FERTILITY RATE(S)...
1.895
FERTILITY AGE DISTRIBUTION(S)...
.147 .312 .312 .166 .052 .011
INFANT MORTALITY RATE(S)...
12.40
EXPECTATION OF LIFE AT BIRTH CORRESPONDING TO
IMR FOR FIRST
PROJECTION PERIOD = 74.88
BASE‑YEAR POPULATION AND SURVIVAL
PROBABILITIES FOR FIRST PROJECTION PERIOD...
MALE FEMALE MALE
FEMALE
0 .9829 .9881
0‑4 81135. 77985.
.9976 .9984
5‑9 81998. 78338. .9985
.9991
10‑14 87349. 84452. .9978
.9990
15‑19 102202. 98910. .9966
.9985
20‑24 110406. 107563. .9961
.9979
25‑29 98969. 97716. .9959
.9973
30‑34 88966. 87129. .9950
.9963
35‑39 68665. 70299. .9926
.9944
40‑44 57192. 58062. .9875
.9907
45‑49 53158. 54518. .9780
.9847
50‑54 52687. 58164. .9616
.9754
55‑59 54838. 64593. .9359
.9599
60‑64 53010. 61645. .8962
.9309
65‑69 49484. 57849.
.8340 .8784
70‑74 37322. 44471. .7427
.7926
75+ 40315. 58124. .4952
.5337
TOTAL 1117696. 1159818.
TOTAL BASE‑YEAR POPULATION (POPBASE)
= 2277514.
CRUDE BIRTH RATE FOR BASE YEAR = 16.20
CRUDE DEATH RATE FOR BASE YEAR = 7.80
INFANT MORTALITY RATE FOR BASE YEAR = 12.40
POPULATION (POPPREV) TEN YEARS PRIOR TO BASE
YEAR = 1477415.
AVERAGE CRUDE BIRTH RATE FOR PREVIOUS TEN
YEARS = 16.20
AVERAGE CRUDE DEATH RATE FOR PREVIOUS TEN
YEARS = 7.80
AVERAGE INFANT MORTALITY RATE FOR PREVIOUS TEN
YEARS = 12.40
ANNUAL EXTERNAL MIGRATION RATE(S) (PER 1000)
(EMRATE)...
.000
ANNUAL EXTERNAL MIGRATION NUMBER(S) (IMMNO)...
63450.
POPULATION BY REGION...
BASE YEAR TEN YEARS PRIOR
APACHE 50125. 31069.
COCHISE 62840. 45403.
COCONINO 67693. 43613.
GILA 29357. 23162.
GRAHAM 17405. 12621.
GREENLEE 5960. 5398.
MARICOPA 1310049.
839932.
MOHAVE 53717. 24863.
NAVAJO 63091. 44513.
PIMA 420025. 277939.
PINAL 64166. 47932.
STA.CRUZ
5230. 3570.
YAVAPAI 63940. 34466.
YUMA 63916. 42934.
TOTAL 2277514. 1477415.
TOTAL FERTILITY RATE (TFREST) ESTIMATED FROM
BASE‑YEAR BIRTH RATE = 1.895
TOTAL FERTILITY RATE (TFR) SPECIFIED FOR FIRST
PROJECTION PERIOD = 1.895
GENERAL FERTILITY RATE (BIRTH RATE (BRFF)
PER 1000 FEMALES AGED 15‑44)
FOR BASE YEAR = 71.00
ESTIMATE OF ANNUAL NET EXTERNAL MIGRATION
NUMBER (BASED ON BIRTH RATE
AND DEATH RATE FOR PREVIOUS TEN YEARS)
= 64622.
ESTIMATED ANNUAL RATE PER 1000 = 35.829
ANNUAL NET MIGRATION NUMBER SPECIFIED FOR
FIRST PROJECTION PERIOD = 63450.
ANNUAL NET MIGRATION RATE PER 1000 SPECIFIED
FOR FIRST PROJECTION
PERIOD =
.000
ANNUAL NET MIGRATION (MIG) IMPLIED BY
MIGRATION NUMBER (IMMNO) AND/OR
MIGRATION RATE (EMRATE) SPECIFIED FOR FIRST
PROJECTION PERIOD = 63450.
APPROX ANNUAL RATE PER 1000 POPULATION
(MIGR) = 27.859
ESTIMATES (BY REGION) OF THE ANNUAL INTERNAL
MIGRATION NUMBER AND RATE (PER
1000) BASED ON THE EXTERNAL MIGRATION
ESTIMATE:
RATE
AMOUNT APPROX
EXACT
APACHE
: 151. 3.022
3.852
COCHISE :
‑486. ‑7.727 ‑9.138
COCONINO:
31. .463 .579
GILA
: ‑431. ‑14.684 ‑16.613
GRAHAM
: ‑139. ‑8.002
‑9.445
GREENLEE:
‑160. ‑26.903 ‑28.348
MARICOPA:
1035. .790 .991
MOHAVE
: 1045. 19.454
28.402
NAVAJO
: ‑375. ‑5.950
‑7.120
PIMA
: ‑573. ‑1.363
‑1.684
PINAL
: ‑660. ‑10.290 ‑11.968
STA.CRUZ:
‑19. ‑3.549 ‑4.317
YAVAPAI :
734. 11.479 15.632
YUMA
: ‑154. ‑2.411
‑2.955
TOTAL
: 0.
SPECIFIED AND IMPLIED VALUES (BY REGION) OF
THE ANNUAL INTERNAL MIGRATION
NUMBER AND RATE (PER 1000):
SPECIFIED IMPLIED
AMOUNT RATE
AMOUNT RATE
APACHE
: 151. .000
151. 3.012
COCHISE : 0.
‑9.138 ‑574. ‑9.138
COCONINO:
31. .000 31.
.458
GILA
: 0. ‑16.613 ‑488. ‑16.613
GRAHAM
: 0. ‑9.445 ‑164. ‑9.445
GREENLEE: 0. ‑28.348 ‑169. ‑28.348
MARICOPA:
1035. .000 1035.
.790
MOHAVE
: 1045. .000
1045. 19.454
NAVAJO
: 0. ‑7.120 ‑449. ‑7.120
PIMA
: 0. ‑1.684 ‑707. ‑1.684
PINAL
: 0. ‑11.968 ‑768. ‑11.968
STA.CRUZ: 0.
‑4.317 ‑23. ‑4.317
YAVAPAI :
734. .000 734.
11.480
YUMA
: 0. ‑2.955 ‑189. ‑2.955
CRUDE BIRTH RATE PER 1000 (CBR) FOR FIRST
PROJECTION PERIOD = 15.027
CRUDE DEATH RATE PER 1000 (CDR) FOR FIRST
PROJECTION PERIOD = 9.939
AVERAGE ANNUAL POPULATION GROWTH RATE PER 1000
FOR PREVIOUS TEN YEARS
= 1000((POPBASE/POPPREV(IR))**.1‑1)
= 44.23
PROJECTED POPULATION GROWTH RATE (GIVEN
SPECIFIED PARAMETERS):
1000((POPPROJ/POPBASE)**.2‑1) = 31.55
APPROX. ANNUAL POPULATION GROWTH RATE PER
1000, BASED ON CBR,
CDR, AND MIGR = CBR‑CDR+MIGR = 32.95
TOTAL POPULATION (ALL RACES) = 2718215.
ESTIMATE OF ANNUAL NET EXTERNAL MIGRATION
NUMBER (BASED ON BIRTH RATE AND
DEATH RATE FOR PREVIOUS TEN YEARS; TOTAL
FOR ALL RACES IN THE MODEL)
=
71553.
ESTIMATED ANNUAL RATE PER 1000 = 33.191
Listing
10. PROJ Run for Example 5
(Projection of the Hispanic Population)
DESTINY PLANNING AND FORECASTING COMPUTER
PROGRAM PACKAGE, VERSION 1.0
PROGRAM NAME: PROJ
DATE OF RUN (DD/MM/YYYY): 5/ 6/1995
TIME OF RUN (HH:MM:SS): 12:59:49
PARAMETER FILE NAME: AZ80HC.DAT
GENERAL POPULATION DESCRIPTION:
BASE YEAR: 1980
NO OF FIVE‑YEAR PERIODS TO PROJECT = 2
YEAR: 1990
DISTRIBUTIONAL ANALYSIS OF POPULATN
TOTAL POPULATN = 3702132.
DISTRIBUTION OF POPULATN
BY RACE
HISPANIC
647662.
NON HISP
3054470.
DISTRIBUTION OF POPULATN
BY REGION
APACHE
65014.
COCHISE
98260.
COCONINO
92212.
GILA
38996.
GRAHAM
26019.
GREENLEE
11016.
MARICOPA
1871693.
MOHAVE
80664.
NAVAJO
76668.
PIMA
651822.
PINAL
101675.
STA.CRUZ
26575.
YAVAPAI
92273.
YUMA
111200.
CROSSTABULATION OF POPULATN
BY REGION AND RACE
HISPANIC NON HISP
APACHE
2867. 62147.
COCHISE
29228. 69032.
COCONINO
10332. 81880.
GILA
9098. 29898.
GRAHAM
6958. 19061.
GREENLEE
5633. 5383.
MARICOPA
281931. 1589762.
MOHAVE
3602. 77062.
NAVAJO
5936. 70732.
PIMA
154500. 497322.
PINAL
33174. 68501.
STA.CRUZ
20544. 6031.
YAVAPAI
6584. 85688.
YUMA
36480. 74720.
Listing
11. CHECK Run for Example 6
(Rehabilitation Services, Projection of the Work-Disabled)
DESTINY PLANNING AND FORECASTING COMPUTER
PROGRAM PACKAGE, VERSION 1.0
PROGRAM NAME: CHECK
DATE OF RUN (DD/MM/YYYY): 5/ 6/1995
TIME OF RUN (HH:MM:SS): 13:17:49
NAME OF PARAMETER FILE = AZ803CD.DAT
GENERAL POPULATION DESCRIPTION:
BASE YEAR = 1980
NO OF RACIAL/ETHNIC GROUPS = 3
NO OF REGIONS = 14
VITAL STATISTICS PARAMETER OPTION = 1
LIFE TABLE OPTION = 1
EXTERNAL MIGRATION OPTION = 1
INTERNAL MIGRATION OPTION = 1
SERVICE SYSTEM OPTION = 1
NAME(S) OF RACE ...
WHITE
AMERIND
OTHER
NAME(S) OF REGION ...
APACHE
COCHISE
COCONINO
GILA
GRAHAM
GREENLEE
MARICOPA
MOHAVE
NAVAJO
PIMA
PINAL
STA.CRUZ
YAVAPAI
YUMA
PRINTOUT OF DEMOGRAPHIC PARAMETERS SUPPRESSED.
TARGET/SERVICE POPULATION DESCRIPTION:
WORK‑DISABLED POPULATION (SEVERELY AND
PARTIALLY WORK‑DISABLED)
NO OF TARGET POPULATIONS = 2
SERVICE POPULATION OPTION = 0
NAME(S) OF TARG POP...
WRKDISSV
WRKDISPT
TARGET
POPULATION = WRKDISSV
TYPE OF STRATIFICATION = 2
INCIDENCE/PREVALENCE RATE(S)...
INDEX
RATE
1
.00000000
2
.00840000
3
.02100000
4
.02900000
5
.06300000
6
.11000000
7
.24200000
8 .00000000
9
.00000000
INDICES, BY STRATUM...
0‑4 1
5‑9 1
10‑14 1
15‑19 2
20‑24 3
25‑29 4
30‑34 4
35‑39 5
40‑44 5
45‑49 6
50‑54 6
55‑59 7
60‑64 7
65‑69 1
70‑74 1
75+
1
TARGET
POPULATION = WRKDISPT
TYPE OF STRATIFICATION = 2
INCIDENCE/PREVALENCE RATE(S)...
INDEX
RATE
1
.00000000
2
.01560000
3
.03900000
4
.07000000
5
.08300000
6
.12400000
7
.11800000
8
.00000000
9
.00000000
INDICES, BY STRATUM...
0‑4 1
5‑9 1
10‑14 1
15‑19 2
20‑24 3
25‑29 4
30‑34 4
35‑39 5
40‑44 5
45‑49 6
50‑54 6
55‑59 7
60‑64 7
65‑69 1
70‑74 1
75+
1
Listing
12. PROJ Run for Example 6
(Rehabilitation Services, Projection of the Work-Disabled)
DESTINY PLANNING AND FORECASTING COMPUTER
PROGRAM PACKAGE, VERSION 1.0
PROGRAM NAME: PROJ
DATE OF RUN (DD/MM/YYYY): 5/ 6/1995
TIME OF RUN (HH:MM:SS): 13:18: 6
PARAMETER FILE NAME: AZ803CD.DAT
GENERAL POPULATION DESCRIPTION:
BASE YEAR: 1980
TARGET/SERVICE POPULATION DESCRIPTION:
WORK‑DISABLED POPULATION (SEVERELY AND
PARTIALLY WORK‑DISABLED)
NO OF FIVE‑YEAR PERIODS TO PROJECT = 2
YEAR: 1990
DISTRIBUTIONAL ANALYSIS OF POPULATN
TOTAL POPULATN = 3735219.
DISTRIBUTION OF POPULATN
BY AGE
0‑4 338816.
5‑9 338489.
10‑14 268314.
15‑19 263875.
20‑24
272520.
25‑29 312009.
30‑34 326222.
35‑39 290907.
40‑44 253597.
45‑49 196686.
50‑54 161169.
55‑59 145678.
60‑64 142066.
65‑69 139466.
70‑74 117950.
75+
167454.
DISTRIBUTIONAL ANALYSIS OF WRKDISSV
TOTAL WRKDISSV = 169750.
DISTRIBUTION OF WRKDISSV
BY AGE
0‑4 0.
5‑9 0.
10‑14 0.
15‑19 2217.
20‑24 5723.
25‑29 9048.
30‑34 9460.
35‑39 18327.
40‑44 15977.
45‑49 21635.
50‑54 17729.
55‑59 35254.
60‑64 34380.
65‑69 0.
70‑74 0.
75+ 0.
DISTRIBUTIONAL ANALYSIS OF WRKDISPT
TOTAL WRKDISPT = 182943.
DISTRIBUTION OF WRKDISPT
BY AGE
0‑4 0.
5‑9 0.
10‑14 0.
15‑19 4116.
20‑24 10628.
25‑29 21841.
30‑34 22836.
35‑39 24145.
40‑44 21049.
45‑49 24389.
50‑54 19985.
55‑59 17190.
60‑64 16764.
65‑69 0.
70‑74 0.
75+ 0.
TOTALS OF TARGET POPULATION(S)
WRKDISSV
169750.
WRKDISPT
182943.
Listing
13. CHECK Run for Example 7
(Projection of School Enrollment)
DESTINY PLANNING AND FORECASTING COMPUTER
PROGRAM PACKAGE, VERSION 1.0
PROGRAM NAME: CHECK
DATE OF RUN (DD/MM/YYYY): 5/ 6/1995
TIME OF RUN (HH:MM:SS): 13:25:32
NAME OF PARAMETER FILE = AZ803CE.DAT
GENERAL POPULATION DESCRIPTION:
BASE YEAR = 1980
NO OF RACIAL/ETHNIC GROUPS = 3
NO OF REGIONS = 14
VITAL STATISTICS PARAMETER OPTION = 1
LIFE TABLE OPTION = 1
EXTERNAL MIGRATION OPTION = 1
INTERNAL MIGRATION OPTION = 1
SERVICE SYSTEM OPTION = 1
NAME(S) OF RACE ...
WHITE
AMERIND
OTHER
NAME(S) OF REGION ...
APACHE
COCHISE
COCONINO
GILA
GRAHAM
GREENLEE
MARICOPA
MOHAVE
NAVAJO
PIMA
PINAL
STA.CRUZ
YAVAPAI
YUMA
PRINTOUT OF DEMOGRAPHIC PARAMETERS SUPPRESSED.
TARGET/SERVICE POPULATION DESCRIPTION:
ELEMENTARY & SECONDARY SCHOOL ENROLLMENT;
TEACHERS; SALARIES
NO OF TARGET POPULATIONS = 1
SERVICE POPULATION OPTION = 2
NO OF SERVICES = 1
NO OF RESOURCES = 1
NO OF COST CATEGORIES = 1
NAME(S) OF TARG POP...
STUDENTS
NAME(S) OF SERV POP...
ELEM/SEC
NAME(S) OF SERVICE ...
TEACHING
NAME(S) OF RESOURCE...
TEACHERS
NAME(S) OF COST ...
SALARIES
SERVICE PARAMETERS FOR SERVICE POPULATION =
ELEM/SEC
TEACHING 1.0000
RESOURCE PARAMETERS FOR SERVICE = TEACHING
TEACHERS .0500
COST PARAMETERS FOR RESOURCE = TEACHERS
SALARIES
17200.0000
TARGET
POPULATION = STUDENTS
TYPE OF STRATIFICATION = 2
INCIDENCE/PREVALENCE RATE(S)...
INDEX
RATE
1
.14300000
2
.95200000
3
.96300000
4
.71700000
5
.21500000
6
.09000000
7
.06200000
8
.00000000
9
.00000000
INDICES, BY STRATUM...
0‑4 1
5‑9 2
10‑14 3
15‑19 4
20‑24 5
25‑29 6
30‑34 7
35‑39 8
40‑44 8
45‑49 8
50‑54 8
55‑59 8
60‑64 8
65‑69 8
70‑74 8
75+
8
SERVICE
POPULATION = ELEM/SEC
TYPE OF STRATIFICATION = 2
SERVICE RATIO(S)...
INDEX
RATE
1
1.00000000
2
.87400000
3
.00000000
4
.00000000
5
.00000000
6
.00000000
7
.00000000
8
.00000000
9
.00000000
INDICES, BY STRATUM...
0‑4 1
5‑9 1
10‑14 1
15‑19 2
20‑24 3
25‑29 3
30‑34 3
35‑39 3
40‑44 3
45‑49 3
50‑54 3
55‑59 3
60‑64 3
65‑69 3
70‑74 3
75+
3
Listing
14. PROJ Run for Example 7
(Projection of School Enrollment)
DESTINY PLANNING AND FORECASTING COMPUTER
PROGRAM PACKAGE, VERSION 1.0
PROGRAM NAME: PROJ
DATE OF RUN (DD/MM/YYYY): 5/ 6/1995
TIME OF RUN (HH:MM:SS): 13:25:44
PARAMETER FILE NAME: AZ803CE.DAT
GENERAL POPULATION DESCRIPTION:
BASE YEAR: 1980
TARGET/SERVICE POPULATION DESCRIPTION:
ELEMENTARY & SECONDARY SCHOOL ENROLLMENT;
TEACHERS; SALARIES
NO OF FIVE‑YEAR PERIODS TO PROJECT = 2
YEAR: 1990
DISTRIBUTIONAL ANALYSIS OF POPULATN
TOTAL POPULATN = 3735219.
DISTRIBUTION OF POPULATN
BY AGE
0‑4 338816.
5‑9 338489.
10‑14 268314.
15‑19 263875.
20‑24 272520.
25‑29 312009.
30‑34 326222.
35‑39 290907.
40‑44 253597.
45‑49 196686.
50‑54 161169.
55‑59 145678.
60‑64 142066.
65‑69 139466.
70‑74 117950.
75+
167454.
DISTRIBUTION OF POPULATN
BY REGION
APACHE
72497.
COCHISE
97683.
COCONINO
97171.
GILA
40759.
GRAHAM
26383.
GREENLEE 11039.
MARICOPA
1893992.
MOHAVE
83827.
NAVAJO
84127.
PIMA
649633.
PINAL
101590.
STA.CRUZ
24075.
YAVAPAI
95609.
YUMA
108068.
DISTRIBUTIONAL ANALYSIS OF STUDENTS
TOTAL STUDENTS = 925175.
DISTRIBUTION OF STUDENTS
BY AGE
0‑4 48451.
5‑9 322241.
10‑14 258386.
15‑19 189199.
20‑24 58592.
25‑29 28081.
30‑34 20226.
35‑39 0.
40‑44 0.
45‑49 0.
50‑54 0.
55‑59 0.
60‑64 0.
65‑69 0.
70‑74 0.
75+ 0.
DISTRIBUTION OF STUDENTS
BY REGION
APACHE
22833.
COCHISE
23786.
COCONINO
26060.
GILA
10332.
GRAHAM
6812.
GREENLEE
2769.
MARICOPA
457268.
MOHAVE
19512.
NAVAJO
24616.
PIMA
159357.
PINAL
26920.
STA.CRUZ
5960.
YAVAPAI
22237.
YUMA
27238.
DISTRIBUTIONAL ANALYSIS OF ELEM/SEC
TOTAL ELEM/SEC = 794438.
DISTRIBUTION OF ELEM/SEC
BY AGE
0‑4 48451.
5‑9 322241.
10‑14 258386.
15‑19 165360.
20‑24 0.
25‑29 0.
30‑34 0.
35‑39 0.
40‑44 0.
45‑49 0.
50‑54 0.
55‑59 0.
60‑64 0.
65‑69 0.
70‑74 0.
75+ 0.
DISTRIBUTION OF ELEM/SEC
BY REGION
APACHE
19933.
COCHISE
20393.
COCONINO
22522.
GILA
8897.
GRAHAM
5865.
GREENLEE
2377.
MARICOPA
392016.
MOHAVE
16710.
NAVAJO
21394.
PIMA
136725.
PINAL
23184.
STA.CRUZ
5112.
YAVAPAI
19040.
YUMA
23393.
DISTRIBUTIONAL ANALYSIS OF TEACHING
TOTAL TEACHING = 794438.
DISTRIBUTION OF TEACHING
BY AGE
0‑4 48451.
5‑9 322241.
10‑14 258386.
15‑19 165360.
20‑24 0.
25‑29 0.
30‑34
0.
35‑39 0.
40‑44 0.
45‑49 0.
50‑54 0.
55‑59 0.
60‑64 0.
65‑69 0.
70‑74 0.
75+ 0.
DISTRIBUTION OF TEACHING
BY REGION
APACHE
19933.
COCHISE
20393.
COCONINO
22522.
GILA
8897.
GRAHAM
5865.
GREENLEE
2377.
MARICOPA
392016.
MOHAVE
16710.
NAVAJO
21394.
PIMA
136725.
PINAL
23184.
STA.CRUZ
5112.
YAVAPAI
19040.
YUMA
23393.
DISTRIBUTIONAL ANALYSIS OF TEACHERS
TOTAL TEACHERS = 39722.
DISTRIBUTION OF TEACHERS
BY AGE
0‑4 2423.
5‑9 16112.
10‑14 12919.
15‑19 8268.
20‑24
0.
25‑29 0.
30‑34 0.
35‑39 0.
40‑44 0.
45‑49 0.
50‑54 0.
55‑59 0.
60‑64 0.
65‑69 0.
70‑74 0.
75+ 0.
DISTRIBUTION OF TEACHERS
BY REGION
APACHE
997.
COCHISE
1020.
COCONINO
1126.
GILA
445.
GRAHAM
293.
GREENLEE
119.
MARICOPA
19601.
MOHAVE
836.
NAVAJO
1070.
PIMA
6836.
PINAL
1159.
STA.CRUZ
256.
YAVAPAI
952.
YUMA
1170.
DISTRIBUTIONAL ANALYSIS OF SALARIES
TOTAL SALARIES = 683216526.
DISTRIBUTION OF SALARIES
BY AGE
0‑4 41667598.
5‑9
277127660.
10‑14
222212066.
15‑19
142209203.
20‑24 0.
25‑29 0.
30‑34 0.
35‑39 0.
40‑44 0.
45‑49 0.
50‑54 0.
55‑59 0.
60‑64 0.
65‑69 0.
70‑74 0.
75+ 0.
DISTRIBUTION OF SALARIES
BY REGION
APACHE
17142535.
COCHISE
17538363.
COCONINO
19369276.
GILA
7650993.
GRAHAM
5044023.
GREENLEE
2044383.
MARICOPA
337133416.
MOHAVE
14370726.
NAVAJO
18399076.
PIMA
117583189.
PINAL
19938284.
STA.CRUZ
4396677.
YAVAPAI
16374272.
YUMA
20118045.
Listing
15. CHECK Run for Example 8 (Criminal
Justice, Projection of Prison Admissions and Operating Cost)
DESTINY PLANNING AND FORECASTING COMPUTER
PROGRAM PACKAGE, VERSION 1.0
PROGRAM NAME: CHECK
DATE OF RUN (DD/MM/YYYY): 5/ 6/1995
TIME OF RUN (HH:MM:SS): 13:29: 1
NAME OF PARAMETER FILE = AZ803CP.DAT
GENERAL POPULATION DESCRIPTION:
BASE YEAR = 1980
NO OF RACIAL/ETHNIC GROUPS = 3
NO OF REGIONS = 14
VITAL STATISTICS PARAMETER OPTION = 1
LIFE TABLE OPTION = 1
EXTERNAL MIGRATION OPTION = 1
INTERNAL MIGRATION OPTION = 1
SERVICE SYSTEM OPTION = 1
NAME(S) OF RACE ...
WHITE
AMERIND
OTHER
NAME(S) OF REGION ...
APACHE
COCHISE
COCONINO
GILA
GRAHAM
GREENLEE
MARICOPA
MOHAVE
NAVAJO
PIMA
PINAL
STA.CRUZ
YAVAPAI
YUMA
PRINTOUT OF DEMOGRAPHIC PARAMETERS SUPPRESSED.
TARGET/SERVICE POPULATION DESCRIPTION:
PRISON ADMISSIONS; PRISON CELLS; OBLIGATED
OPERATING COST
NO OF TARGET POPULATIONS = 1
SERVICE POPULATION OPTION = 2
NO OF SERVICES = 1
NO OF RESOURCES = 1
NO OF COST CATEGORIES = 1
NAME(S) OF TARG POP...
ADMIS'NS
NAME(S) OF SERV POP...
SENTYR
NAME(S) OF SERVICE ...
INCARC'N
NAME(S) OF RESOURCE...
CELL
NAME(S) OF COST ...
OP COST
SERVICE PARAMETERS FOR SERVICE POPULATION =
SENTYR
INCARC'N 1.0000
RESOURCE PARAMETERS FOR SERVICE = INCARC'N
CELL 1.0000
COST PARAMETERS FOR RESOURCE = CELL
OP COST
16000.0000
TARGET
POPULATION = ADMIS'NS
TYPE OF STRATIFICATION = 5
INCIDENCE/PREVALENCE RATE(S)...
INDEX
RATE
1
.00000000
2
.00200000
3
.00400000
4
.00300000
5
.00100000
6
.00030000
7
.00007000
8
.00020000
9
.00002000
INDICES, BY STRATUM...
MALE
0‑4 1
5‑9 1
10‑14 1
15‑19 2
20‑24 3
25‑29 4
30‑34 2
35‑39 5
40‑44 5
45‑49 5
50‑54 5
55‑59 6
60‑64 7
65‑69 7
70‑74 7
75+
7
FEMALE
0‑4 1
5‑9 1
10‑14 1
15‑19 8
20‑24 8
25‑29 8
30‑34 8
35‑39 7
40‑44 7
45‑49 7
50‑54 9
55‑59 9
60‑64 1
65‑69 1
70‑74 1
75+
1
SERVICE
POPULATION = SENTYR
TYPE OF STRATIFICATION = 3
SERVICE RATIO(S)...
MALE
3.00000000
FEMALE
2.30000000
Listing
16. PROJ Run for Example 8 (Criminal
Justice, Projection of Prison Admissions and Operating Cost)
DESTINY PLANNING AND FORECASTING COMPUTER
PROGRAM PACKAGE, VERSION 1.0
PROGRAM NAME: PROJ
DATE OF RUN (DD/MM/YYYY): 5/ 6/1995
TIME OF RUN (HH:MM:SS): 13:29:55
PARAMETER FILE NAME: AZ803CP.DAT
GENERAL POPULATION DESCRIPTION:
BASE YEAR: 1980
TARGET/SERVICE POPULATION DESCRIPTION:
PRISON ADMISSIONS; PRISON CELLS; OBLIGATED
OPERATING COST
NO OF FIVE‑YEAR PERIODS TO PROJECT = 2
YEAR: 1990
DISTRIBUTIONAL ANALYSIS OF POPULATN
TOTAL POPULATN = 3735219.
DISTRIBUTION OF POPULATN
BY SEX
MALE
1849940.
FEMALE
1885279.
DISTRIBUTIONAL ANALYSIS OF ADMIS'NS
TOTAL ADMIS'NS = 2262.
DISTRIBUTION OF ADMIS'NS
BY SEX
MALE
2118.
FEMALE
145.
DISTRIBUTIONAL ANALYSIS OF SENTYR
TOTAL SENTYR
= 6686.
DISTRIBUTION OF SENTYR
BY SEX
MALE
6353.
FEMALE
333.
DISTRIBUTIONAL ANALYSIS OF INCARC'N
TOTAL INCARC'N = 6686.
DISTRIBUTION OF INCARC'N
BY SEX
MALE
6353.
FEMALE
333.
DISTRIBUTIONAL ANALYSIS OF CELL
TOTAL CELL
= 6686.
DISTRIBUTION OF CELL
BY SEX
MALE
6353.
FEMALE
333.
DISTRIBUTIONAL ANALYSIS OF OP COST
TOTAL OP COST
= 106971223.
DISTRIBUTION OF OP COST
BY SEX
MALE
101648203.
FEMALE
5323019.
Listing
17. CHECK Run for Example 9 (Health Care,
Projection of the Need for Short-Term and Long-Term Beds)
DESTINY PLANNING AND FORECASTING COMPUTER
PROGRAM PACKAGE, VERSION 1.0
PROGRAM NAME: CHECK
DATE OF RUN (DD/MM/YYYY): 5/ 6/1995
TIME OF RUN (HH:MM:SS): 13:32:33
NAME OF PARAMETER FILE = AZ803CH.DAT
GENERAL POPULATION DESCRIPTION:
BASE YEAR = 1980
NO OF RACIAL/ETHNIC GROUPS = 3
NO OF REGIONS = 14
VITAL STATISTICS PARAMETER OPTION = 1
LIFE TABLE OPTION = 1
EXTERNAL MIGRATION OPTION = 1
INTERNAL MIGRATION OPTION = 1
SERVICE SYSTEM OPTION = 1
NAME(S) OF RACE ...
WHITE
AMERIND
OTHER
NAME(S) OF REGION ...
APACHE
COCHISE
COCONINO
GILA
GRAHAM
GREENLEE
MARICOPA
MOHAVE
NAVAJO
PIMA
PINAL
STA.CRUZ
YAVAPAI
YUMA
PRINTOUT OF DEMOGRAPHIC PARAMETERS SUPPRESSED.
TARGET/SERVICE POPULATION DESCRIPTION:
NEED FOR SHORT‑TERM & LONG‑TERM
BEDS (LONG‑TERM: NURSING, PSYCH, MENTAL HAND.)
NO OF TARGET POPULATIONS = 4
SERVICE POPULATION OPTION = 0
NAME(S) OF TARG POP...
ST BEDS
NH BEDS
PSY BEDS
MH BEDS
TARGET
POPULATION = ST BEDS
TYPE OF STRATIFICATION = 2
INCIDENCE/PREVALENCE RATE(S)...
INDEX
RATE
1
.00142000
2
.00056000
3
.00175000
4
.00242000
5
.00255000
6
.00428000
7
.01114000
8
.00000000
9
.00000000
INDICES, BY STRATUM...
0‑4 1
5‑9 2
10‑14 2
15‑19 3
20‑24 3
25‑29 4
30‑34 4
35‑39 5
40‑44 5
45‑49 6
50‑54 6
55‑59 6
60‑64 6
65‑69 7
70‑74 7
75+
7
TARGET
POPULATION = NH BEDS
TYPE OF STRATIFICATION = 5
INCIDENCE/PREVALENCE RATE(S)...
INDEX
RATE
1
.00015000
2
.00120000
3
.01100000
4
.06300000
5
.01200000
6
.09700000
7
.00000000
8
.00000000
9
.00000000
INDICES, BY STRATUM...
MALE
0‑4 1
5‑9 1
10‑14 1
15‑19 1
20‑24 2
25‑29 2
30‑34 2
35‑39 2
40‑44 2
45‑49 2
50‑54 2
55‑59 2
60‑64 2
65‑69 3
70‑74 3
75+
4
FEMALE
0‑4 1
5‑9 1
10‑14 1
15‑19 1
20‑24 2
25‑29 2
30‑34 2
35‑39 2
40‑44 2
45‑49 2
50‑54 2
55‑59 2
60‑64 2
65‑69 5
70‑74 5
75+
6
TARGET
POPULATION = PSY BEDS
TYPE OF STRATIFICATION = 2
INCIDENCE/PREVALENCE RATE(S)...
INDEX
RATE
1
.00046000
2
.00024000
3
.00020000
4
.00000000
5
.00000000
6
.00000000
7
.00000000
8
.00000000
9
.00000000
INDICES, BY STRATUM...
0‑4 1
5‑9 1
10‑14 1
15‑19 1
20‑24 2
25‑29 2
30‑34 2
35‑39 2
40‑44 2
45‑49 2
50‑54 2
55‑59 2
60‑64 2
65‑69 3
70‑74 3
75+
3
TARGET
POPULATION = MH BEDS
TYPE OF STRATIFICATION = 2
INCIDENCE/PREVALENCE RATE(S)...
INDEX
RATE
1
.00092000
2
.00095000
3
.00024000
4
.00000000
5
.00000000
6
.00000000
7
.00000000
8
.00000000
9
.00000000
INDICES, BY STRATUM...
0‑4 1
5‑9 1
10‑14 1
15‑19 1
20‑24 2
25‑29 2
30‑34 2
35‑39 2
40‑44 2
45‑49 2
50‑54 2
55‑59 2
60‑64 2
65‑69 3
70‑74 3
75+
3
Listing
18. PROJ Run for Example 9 (Health
Care, Projection of the Need for Short-Term and Long-Term Beds)
DESTINY PLANNING AND FORECASTING COMPUTER
PROGRAM PACKAGE, VERSION 1.0
PROGRAM NAME: PROJ
DATE OF RUN (DD/MM/YYYY): 5/ 6/1995
TIME OF RUN (HH:MM:SS): 13:32:50
PARAMETER FILE NAME: AZ803CH.DAT
GENERAL POPULATION DESCRIPTION:
BASE YEAR: 1980
TARGET/SERVICE POPULATION DESCRIPTION:
NEED FOR SHORT‑TERM & LONG‑TERM
BEDS (LONG‑TERM: NURSING, PSYCH, MENTAL HAND.)
NO OF FIVE‑YEAR PERIODS TO PROJECT = 2
DISTRIBUTIONAL ANALYSIS OF POPULATN
TOTAL POPULATN = 2718215.
TOTALS OF TARGET POPULATION(S)
ST BEDS
8883.
NH BEDS
13025.
PSY BEDS
837.
MH BEDS
2337.
YEAR: 1981
DISTRIBUTIONAL ANALYSIS OF POPULATN
TOTAL POPULATN = 2819125.
TOTALS OF TARGET POPULATION(S)
ST BEDS
9219.
NH BEDS
13656.
PSY BEDS
867.
MH BEDS
2423.
YEAR: 1982
DISTRIBUTIONAL ANALYSIS OF POPULATN
TOTAL POPULATN = 2920035.
TOTALS OF TARGET POPULATION(S)
ST BEDS
9555.
NH BEDS
14287.
PSY BEDS
897.
MH BEDS
2510.
YEAR: 1983
DISTRIBUTIONAL ANALYSIS OF POPULATN
TOTAL POPULATN = 3020944.
TOTALS OF TARGET POPULATION(S)
ST BEDS
9891.
NH BEDS
14918.
PSY BEDS
927.
MH BEDS
2596.
YEAR: 1984
DISTRIBUTIONAL ANALYSIS OF POPULATN
TOTAL POPULATN = 3121854.
TOTALS OF TARGET POPULATION(S)
ST BEDS
10227.
NH BEDS
15549.
PSY BEDS
957.
MH BEDS
2682.
YEAR: 1985
DISTRIBUTIONAL ANALYSIS OF POPULATN
TOTAL POPULATN = 3222764.
TOTALS OF TARGET POPULATION(S)
ST BEDS
10563.
NH BEDS
16180.
PSY BEDS
986.
MH BEDS
2768.
YEAR: 1986
DISTRIBUTIONAL ANALYSIS OF POPULATN
TOTAL POPULATN = 3325255.
TOTALS OF TARGET POPULATION(S)
ST BEDS
10889.
NH BEDS
16852.
PSY BEDS
1018.
MH BEDS
2857.
YEAR: 1987
DISTRIBUTIONAL ANALYSIS OF POPULATN
TOTAL POPULATN = 3427746.
TOTALS OF TARGET POPULATION(S)
ST BEDS
11214.
NH BEDS
17523.
PSY BEDS
1050.
MH BEDS
2945.
YEAR: 1988
DISTRIBUTIONAL ANALYSIS OF POPULATN
TOTAL POPULATN = 3530237.
TOTALS OF TARGET POPULATION(S)
ST BEDS
11539.
NH BEDS
18195.
PSY BEDS
1082.
MH BEDS
3034.
YEAR: 1989
DISTRIBUTIONAL ANALYSIS OF POPULATN
TOTAL POPULATN = 3632728.
TOTALS OF TARGET POPULATION(S)
ST BEDS
11864.
NH BEDS
18867.
PSY BEDS
1114.
MH BEDS
3122.
YEAR: 1990
DISTRIBUTIONAL ANALYSIS OF POPULATN
TOTAL POPULATN = 3735219.
TOTALS OF TARGET POPULATION(S)
ST BEDS
12189.
NH BEDS
19538.
PSY BEDS
1146.
MH BEDS
3211.
Listing
19. CHECK Run for Example 10 (Social
Services, Projection of Counselors and Budget Needed to Provide Social Services
to the Elderly Population)
DESTINY PLANNING AND FORECASTING COMPUTER
PROGRAM PACKAGE, VERSION 1.0
PROGRAM NAME: CHECK
DATE OF RUN (DD/MM/YYYY): 5/ 6/1995
TIME OF RUN (HH:MM:SS): 13:36:38
NAME OF PARAMETER FILE = AZ803CS.DAT
GENERAL POPULATION DESCRIPTION:
BASE YEAR = 1980
NO OF RACIAL/ETHNIC GROUPS = 3
NO OF REGIONS = 14
VITAL STATISTICS PARAMETER OPTION = 1
LIFE TABLE OPTION = 1
EXTERNAL MIGRATION OPTION = 1
INTERNAL MIGRATION OPTION = 1
SERVICE SYSTEM OPTION = 1
NAME(S) OF RACE ...
WHITE
AMERIND
OTHER
NAME(S) OF REGION ...
APACHE
COCHISE
COCONINO
GILA
GRAHAM
GREENLEE
MARICOPA
MOHAVE
NAVAJO
PIMA
PINAL
STA.CRUZ
YAVAPAI
YUMA
PRINTOUT OF DEMOGRAPHIC PARAMETERS SUPPRESSED.
TARGET/SERVICE POPULATION DESCRIPTION:
SOCIAL SERVICES FOR THE ELDERLY; 8 SERVICES, 3
RESOURCES, 3 COST CATEGORIES
NO OF TARGET POPULATIONS = 1
SERVICE POPULATION OPTION = 2
NO OF SERVICES = 7
NO OF RESOURCES = 3
NO OF COST CATEGORIES = 3
NAME(S) OF TARG POP...
ELDERLY
NAME(S) OF SERV POP...
ELDR(SV)
NAME(S) OF SERVICE ...
COUNSLNG
CHORE SV
HOMEMAKR
SUBSCARE
DAY CARE
TRANSPRT
OTHER
NAME(S) OF RESOURCE...
COUNSELR
PURCHSVC
PAYMENTS
NAME(S) OF COST ...
DIRCTSV$
PURCHSV$
PAYMENT$
SERVICE PARAMETERS FOR SERVICE POPULATION =
ELDR(SV)
COUNSLNG 2.0000
CHORE SV 16.0000
HOMEMAKR 750.0000
SUBSCARE 12.0000
DAY CARE 7.0000
TRANSPRT 10.0000
OTHER 10.0000
RESOURCE PARAMETERS FOR SERVICE = COUNSLNG
COUNSELR 1.0000
PURCHSVC .0000
PAYMENTS .0000
RESOURCE PARAMETERS FOR SERVICE = CHORE SV
COUNSELR .0000
PURCHSVC 1.0000
PAYMENTS .0000
RESOURCE PARAMETERS FOR SERVICE = HOMEMAKR
COUNSELR .0000
PURCHSVC 1.0000
PAYMENTS .0000
RESOURCE PARAMETERS FOR SERVICE = SUBSCARE
COUNSELR .0000
PURCHSVC 1.0000
PAYMENTS .0000
RESOURCE PARAMETERS FOR SERVICE = DAY CARE
COUNSELR .0000
PURCHSVC 1.0000
PAYMENTS .0000
RESOURCE PARAMETERS FOR SERVICE = TRANSPRT
COUNSELR .0000
PURCHSVC .5000
PAYMENTS .5000
RESOURCE PARAMETERS FOR SERVICE = OTHER
COUNSELR .0000
PURCHSVC .5000
PAYMENTS .5000
COST PARAMETERS FOR RESOURCE = COUNSELR
DIRCTSV$ 15.0000
PURCHSV$ .0000
PAYMENT$ .0000
COST PARAMETERS FOR RESOURCE = PURCHSVC
DIRCTSV$ .0000
PURCHSV$ 1.0000
PAYMENT$ .0000
COST PARAMETERS FOR RESOURCE = PAYMENTS
DIRCTSV$ .0000
PURCHSV$ .0000
PAYMENT$ 1.0000
TARGET
POPULATION = ELDERLY
TYPE OF STRATIFICATION = 2
INCIDENCE/PREVALENCE RATE(S)...
INDEX
RATE
1
.00000000
2
1.00000000
3
.00000000
4
.00000000
5
.00000000
6
.00000000
7
.00000000
8
.00000000
9
.00000000
INDICES, BY STRATUM...
0‑4 1
5‑9 1
10‑14 1
15‑19 1
20‑24 1
25‑29 1
30‑34 1
35‑39 1
40‑44 1
45‑49 1
50‑54 1
55‑59 1
60‑64 1
65‑69 2
70‑74 2
75+
2
SERVICE
POPULATION = ELDR(SV)
TYPE OF STRATIFICATION = 2
SERVICE RATIO(S)...
INDEX
RATE
1
.00000000
2
.03000000
3
.05000000
4
.07000000
5
.00000000
6
.00000000
7
.00000000
8
.00000000
9
.00000000
INDICES, BY STRATUM...
0‑4 1
5‑9 1
10‑14 1
15‑19 1
20‑24 1
25‑29 1
30‑34 1
35‑39 1
40‑44 1
45‑49 1
50‑54 1
55‑59 1
60‑64 1
65‑69 2
70‑74 3
75+
4
Listing
20. PROJ Run for Example 10 (Social
Services, Projection of Counselors and Budget Needed to Provide Social Services
to the Elderly Population)
DESTINY PLANNING AND FORECASTING COMPUTER
PROGRAM PACKAGE, VERSION 1.0
PROGRAM NAME: PROJ
DATE OF RUN (DD/MM/YYYY): 5/ 6/1995
TIME OF RUN (HH:MM:SS):
PARAMETER FILE NAME: AZ803CS.DAT
GENERAL POPULATION DESCRIPTION:
BASE YEAR: 1980
TARGET/SERVICE POPULATION DESCRIPTION:
SOCIAL SERVICES FOR THE ELDERLY; 8 SERVICES, 3
RESOURCES, 3 COST CATEGORIES
NO OF FIVE‑YEAR PERIODS TO PROJECT = 1
YEAR: 1983
DISTRIBUTIONAL ANALYSIS OF POPULATN
TOTAL POPULATN = 3020944.
DISTRIBUTION OF POPULATN
BY SEX
MALE
1490114.
FEMALE
1530830.
DISTRIBUTION OF POPULATN
BY REGION
APACHE
56418.
COCHISE
86046.
COCONINO
78946.
GILA
37068.
GRAHAM
23057.
GREENLEE
10853.
MARICOPA
1564786.
MOHAVE
62054.
NAVAJO
70367.
PIMA
545662.
PINAL
90021.
STA.CRUZ
20673.
YAVAPAI
73847.
DISTRIBUTIONAL ANALYSIS OF ELDERLY
TOTAL ELDERLY
= 344542.
DISTRIBUTION OF ELDERLY
BY SEX
MALE
151885.
FEMALE
192658.
DISTRIBUTION OF ELDERLY
BY REGION
APACHE
3592.
COCHISE
10119.
COCONINO
7908.
GILA
4198.
GRAHAM
2481.
GREENLEE
1232.
MARICOPA
186166.
MOHAVE
7886.
NAVAJO
5903.
PIMA
63245.
PINAL
9106.
STA.CRUZ
2345.
YAVAPAI
9390.
YUMA
10114.
DISTRIBUTIONAL ANALYSIS OF ELDR(SV)
TOTAL ELDR(SV) = 17254.
DISTRIBUTION OF ELDR(SV)
BY SEX
MALE
7505.
FEMALE
9748.
DISTRIBUTION OF ELDR(SV)
BY REGION
APACHE
181.
COCHISE
507.
COCONINO
396.
GILA
210.
GRAHAM
124.
GREENLEE 62.
MARICOPA
9322.
MOHAVE
395.
NAVAJO
296.
PIMA
3167.
PINAL
456.
STA.CRUZ
117.
YAVAPAI
470.
DISTRIBUTIONAL ANALYSIS OF COUNSLNG
TOTAL COUNSLNG = 34507.
DISTRIBUTION OF COUNSLNG
BY SEX
MALE
15010.
FEMALE
19497.
DISTRIBUTION OF COUNSLNG
BY REGION
APACHE
361.
COCHISE
1013.
COCONINO
793.
GILA
421.
GRAHAM
248.
GREENLEE
123.
MARICOPA
18645.
MOHAVE
790.
NAVAJO
592.
PIMA
6334.
PINAL
911.
STA.CRUZ
235.
YAVAPAI
941.
DISTRIBUTIONAL ANALYSIS OF CHORE SV
TOTAL CHORE SV = 276057.
DISTRIBUTION OF CHORE SV
BY SEX
MALE
120083.
FEMALE
155973.
DISTRIBUTION OF CHORE SV
BY REGION
APACHE
2890.
COCHISE
8106.
COCONINO
6343.
GILA
3366.
GRAHAM
1988.
GREENLEE
987.
MARICOPA
149160.
MOHAVE
6322.
NAVAJO
4740.
PIMA
50668.
PINAL
7292.
STA.CRUZ
1878.
YAVAPAI
7527.
DISTRIBUTIONAL ANALYSIS OF HOMEMAKR
TOTAL HOMEMAKR = 12940160.
DISTRIBUTION OF HOMEMAKR
BY SEX
MALE
5628914.
FEMALE
7311246.
DISTRIBUTION OF HOMEMAKR
BY REGION
APACHE
135452.
COCHISE
379987.
COCONINO
297316.
GILA
157762.
GRAHAM
93181.
GREENLEE
46267.
MARICOPA
6991865.
MOHAVE
296350.
NAVAJO
222174.
PIMA
2375079.
PINAL
341809.
STA.CRUZ
88026.
YAVAPAI
352815.
DISTRIBUTIONAL ANALYSIS OF SUBSCARE
TOTAL SUBSCARE = 207043.
DISTRIBUTION OF SUBSCARE
BY SEX
MALE
90063.
FEMALE
116980.
DISTRIBUTION OF SUBSCARE
BY REGION
APACHE
2167.
COCHISE
6080.
COCONINO
4757.
GILA
2524.
GRAHAM
1491.
GREENLEE
740.
MARICOPA
111870.
MOHAVE
4742.
NAVAJO
3555.
PIMA
38001.
PINAL
5469.
STA.CRUZ
1408.
YAVAPAI
5645.
DISTRIBUTIONAL ANALYSIS OF DAY CARE
TOTAL DAY CARE = 120775.
DISTRIBUTION OF DAY CARE
BY SEX
MALE
52537.
FEMALE
68238.
DISTRIBUTION OF DAY CARE
BY REGION
APACHE
1264.
COCHISE
3547.
COCONINO
2775.
GILA
1472.
GRAHAM
870.
GREENLEE
432.
MARICOPA
65257.
MOHAVE
2766.
NAVAJO
2074.
PIMA
22167.
PINAL
3190.
STA.CRUZ
822.
YAVAPAI
3293.
DISTRIBUTIONAL ANALYSIS OF TRANSPRT
TOTAL TRANSPRT = 172535.
DISTRIBUTION OF TRANSPRT
BY SEX
MALE
75052.
FEMALE
97483.
DISTRIBUTION OF TRANSPRT
BY REGION
APACHE
1806.
COCHISE
5066.
COCONINO
3964.
GILA
2103.
GRAHAM
1242.
GREENLEE
617.
MARICOPA
93225.
MOHAVE
3951.
NAVAJO
2962.
PIMA
31668.
PINAL
4557.
STA.CRUZ
1174.
YAVAPAI
4704.
YUMA
5062.
DISTRIBUTIONAL ANALYSIS OF OTHER
TOTAL OTHER
= 172535.
DISTRIBUTION OF OTHER
BY SEX
MALE
75052.
FEMALE
97483.
DISTRIBUTION OF OTHER
BY REGION
APACHE
1806.
COCHISE
5066.
COCONINO
3964.
GILA
2103.
GRAHAM 1242.
GREENLEE
617.
MARICOPA
93225.
MOHAVE
3951.
NAVAJO
2962.
PIMA
31668.
PINAL
4557.
STA.CRUZ
1174.
YAVAPAI
4704.
YUMA
5062.
TOTALS OF SERVICE(S)
COUNSLNG
34507.
CHORE SV
276057.
HOMEMAKR
12940160.
SUBSCARE
207043.
DAY CARE
120775.
TRANSPRT
172535.
OTHER
172535.
DISTRIBUTION OF SERVICE(S)
BY SERVED POPULATION(S)
COUNSLNG CHORE SV
HOMEMAKR SUBSCARE DAY CARE
TRANSPRT OTHER
ELDR(SV)
34507. 276057. 12940160.
207043. 120775. 172535.
172535.
TOTAL
34507. 276057. 12940160.
207043. 120775. 172535.
172535.
DISTRIBUTIONAL ANALYSIS OF COUNSELR
TOTAL COUNSELR = 34507.
DISTRIBUTION OF COUNSELR
BY SEX
MALE
15010.
FEMALE
19497.
DISTRIBUTION OF COUNSELR
BY REGION
APACHE
361.
COCHISE
1013.
COCONINO
793.
GILA
421.
GRAHAM
248.
GREENLEE
123.
MARICOPA
18645.
MOHAVE
790.
NAVAJO
592.
PIMA
6334.
PINAL
911.
STA.CRUZ
235.
YAVAPAI
941.
YUMA
1012.
DISTRIBUTIONAL ANALYSIS OF PURCHSVC
TOTAL PURCHSVC = 13716570.
DISTRIBUTION OF PURCHSVC
BY SEX
MALE
5966649.
FEMALE
7749921.
DISTRIBUTION OF PURCHSVC
BY REGION
APACHE
143580.
COCHISE
402786.
COCONINO
315155.
GILA
167228.
GRAHAM
98772.
GREENLEE
49043.
MARICOPA
7411377.
MOHAVE
314131.
NAVAJO
235504.
PIMA
2517584.
PINAL
362317.
STA.CRUZ
93307.
YAVAPAI
373984.
YUMA
402462.
DISTRIBUTIONAL ANALYSIS OF PAYMENTS
TOTAL PAYMENTS = 172535.
DISTRIBUTION OF PAYMENTS
BY SEX
MALE
75052.
FEMALE
97483.
DISTRIBUTION OF PAYMENTS
BY REGION
APACHE
1806.
COCHISE
5066.
COCONINO
3964.
GILA
2103.
GRAHAM
1242.
GREENLEE
617.
MARICOPA
93225.
MOHAVE
3951.
NAVAJO
2962.
PIMA
31668.
PINAL
4557.
STA.CRUZ
1174.
YAVAPAI
4704.
TOTALS OF RESOURCE(S)
COUNSELR
34507.
PURCHSVC
13716570.
PAYMENTS
172535.
DISTRIBUTION OF RESOURCE(S)
BY SERVED POPULATION(S)
COUNSELR PURCHSVC
PAYMENTS
ELDR(SV)
34507. 13716570. 172535.
TOTAL
34507. 13716570. 172535.
DISTRIBUTION OF RESOURCE(S)
BY SERVICE(S)
COUNSELR PURCHSVC
PAYMENTS
COUNSLNG
34507. 0. 0.
CHORE SV 0.
276057. 0.
HOMEMAKR 0.
12940160. 0.
SUBSCARE 0.
207043. 0.
DAY CARE 0.
120775. 0.
TRANSPRT 0. 86268. 86268.
OTHER 0. 86268. 86268.
TOTAL
34507. 13716570. 172535.
DISTRIBUTIONAL ANALYSIS OF DIRCTSV$
TOTAL DIRCTSV$ = 517606.
DISTRIBUTION OF DIRCTSV$
BY SEX
MALE
225157.
FEMALE
292450.
DISTRIBUTION OF DIRCTSV$
BY REGION
APACHE
5418.
COCHISE
15199.
COCONINO
11893.
GILA
6310.
GRAHAM
3727.
GREENLEE
1851.
MARICOPA
279675.
MOHAVE
11854.
NAVAJO
8887.
PIMA
95003.
PINAL
13672.
STA.CRUZ
3521.
YAVAPAI
14113.
YUMA 15187.
DISTRIBUTIONAL ANALYSIS OF PURCHSV$
TOTAL PURCHSV$ = 13716570.
DISTRIBUTION OF PURCHSV$
BY SEX
MALE
5966649.
FEMALE
7749921.
DISTRIBUTION OF PURCHSV$
BY REGION
APACHE
143580.
COCHISE
402786.
COCONINO
315155.
GILA
167228.
GRAHAM
98772.
GREENLEE
49043.
MARICOPA
7411377.
MOHAVE
314131.
NAVAJO
235504.
PIMA
2517584.
PINAL
362317.
STA.CRUZ
93307.
YAVAPAI
373984.
YUMA
402462.
DISTRIBUTIONAL ANALYSIS OF PAYMENT$
TOTAL PAYMENT$ = 172535.
DISTRIBUTION OF PAYMENT$
BY SEX
MALE
75052.
FEMALE
97483.
DISTRIBUTION OF PAYMENT$
BY REGION
APACHE
1806.
COCHISE
5066.
COCONINO
3964.
GILA
2103.
GRAHAM
1242.
GREENLEE
617.
MARICOPA
93225.
MOHAVE
3951.
NAVAJO
2962.
PIMA
31668.
PINAL
4557.
STA.CRUZ
1174.
YAVAPAI
4704.
TOTALS OF COST CATEGORY(IES)
DIRCTSV$
517606.
PURCHSV$
13716570.
PAYMENT$
172535.
DISTRIBUTION OF COST CATEGORY(IES)
BY SERVED POPULATION(S)
DIRCTSV$ PURCHSV$
PAYMENT$
ELDR(SV)
517606. 13716570. 172535.
TOTAL
517606. 13716570. 172535.
DISTRIBUTION OF COST CATEGORY(IES)
BY SERVICE(S)
DIRCTSV$ PURCHSV$
PAYMENT$
COUNSLNG
517606. 0. 0.
CHORE SV 0.
276057. 0.
HOMEMAKR 0.
12940160. 0.
SUBSCARE 0.
207043. 0.
DAY CARE 0.
120775. 0.
TRANSPRT 0. 86268. 86268.
OTHER 0. 86268. 86268.
TOTAL
517606. 13716570. 172535.
DISTRIBUTION OF COST CATEGORY(IES)
BY RESOURCE(S)
DIRCTSV$ PURCHSV$
PAYMENT$
COUNSELR
517606. 0. 0.
PURCHSVC 0.
13716570. 0.
PAYMENTS 0.
0. 172535.
TOTAL
517606. 13716570. 172535.