BASIC DEMOGRAPHIC METHODS

1 Nature and scope of Demography

Demography is a scientific study of human population. It focuses on five aspects of human

population, namely:

1.1 Size,
1.2 Distribution,
1.3 Composition,
1.4 Components of population change
1.5 Determinants and consequences of population change

Population size is the number of persons in an area at a given point in time. Population
distribution refers to how population is dispersed in geographic space at a given point in time.
Population composition is usually defined in terms of ascribed characteristics that include
place of birth, sex and age. These characteristics are termed ascribed because they either
never change over a person’s lifetime e.g. place of birth, or change in a highly predictable
manner e.g. age. Many other characteristics also are recognised as within the purview of the
demographer. These fall under social and economic characteristics, such, education level,
school enrolment, labour force status, income and wealth. Achieved characteristics are also
used and include: place of residence, occupation, marital status, and educational attainment,
marital status, household characteristics, and living arrangements. These are termed achieved
characteristics because they can change over a person’s lifetime e.g., place of residence.
Achieved characteristics can vary in ways that may not be very predictable, e.g. occupation.

The components of population change can be defined narrowly or broadly. Defined narrowly
there are three components: births, deaths, and migration. Defined more broadly, the
components include the factors that affect the components of change. Births, for example, are
affected by factors such as family formation, contraception use, and household dissolution.
Deaths are affected by sickness or morbidity, nutrition, the efficacy of public health
measures, and medical advances. Migration is affected by personal characteristics such as
age, occupation, an educational attainment, as well as by other situations which may operate
as push and pull factors.

1
2 BRANCHES OF DEMOGRAPHY

There are two branches of demography, namely;

2.1 Basic Demography

2.2 Applied Demography

Basic Demography: Focuses on theoretical and empirical aspects of demography. It can be

practiced either in the perspective of formal/applied demography or socio-economic aspects.
Basic demography is closely linked to social sciences. Examples of basic demography are:
level of education, religion, ethnicity, race, nationality, etc. Basic demography is sometimes
referred to as Population Studies.

Applied or Formal Demography: Rives and Serow offered their definition as “ the branch of
the discipline that is directed towards the production, dissemination, and analysis of
demographic and closely related information for quite specific purposes of planning and
reporting”. They further observed that Applied Demography “is more concerned with the
measurement and interpretation of current and prospective population change than with
behavioural determinants of its change” (Rives and Serow, 1984:10). They emphasised that
Applied Demographers tend to focus on geographic units and their population characteristics,
while Basic Demographers are more concerned with individual and their demographic
behaviour.

Building on the Rives and Serow definitions, Murdock and Ellis (1991:6) distinguish Basic
from Applied Demography in terms of different emphases across five dimensions:

a) Scientific goal: Basic demography is concerned largely with explanation; Applied

demography with prediction.
b) Time reference: Basic demography is concerned with the past; applied demography
with the present and future.
c) Geographic focus: Basic demography is concerned with international or national
patterns (often studied using individual data); applied demography with aggregate
data for small areas.
d) Purpose of the analysis: Basic demography is concerned with the advance of scientific
knowledge, especially generally theoretical knowledge of causes; applied
demography with the application of knowledge to discern the consequences or
concomitants of demographic change.

2
 e) Intended use of analytic results: Basic demography is concerned with the advance of
knowledge and the sharing of that knowledge with the scientific community and the
general public; applied demography with the use of research results to inform decision
making among non-demographers.

Based on the above differences, Murdock and Ellis (1991:6) suggested that applied
demography should be viewed as that branch of demography that brings about the gain of
knowledge of the consequences and concomitants of demographic change to guide decision
making related to the planning, development, and or distribution of public or private-sector
goods or services for current and future use in the study area/s.

Applied demography requires knowledge both of basic demographic science and of the
means by which it can be applied to address pragmatic and policy-related questions.

The following have been observed regarding applied demography:

i) Applied demography brings demographic expertise to bear on specific, concrete

practical problems.
ii) The above problems arise especially in the realms of business and government,
particularly state and local government.
iii) The problems typically are posed at the level of small geographic areas.
iv) The core analytic activities in applied demography are population estimation and
forecasting.
v) Applied demography is relatively uninterested in theory or in causal explanation.
vi) Applied demographic work is not autonomous scientific activity but is done
specifically for client.

3 IMPORTANCE OF STUDYING DEMOGRAPHY

3.1 Planning for Economy: Studying demography helps to comprehend how the growth
rate of the economy is keeping pace with the population growth rate. If the population
is growing at a faster rate, the pace of development of the economy will be slow. It is
recommended that the economic growth rate should be triple the population growth if
a possible development is to be realised in the economy. If the population growth rate
is higher, the government can take measure to control its growth and accelerate
development of the economy.

3
3.2 Understanding Society: Studying demography enables one to understand the rate at
which population is increasing. If it is increasing rapidly, it leads to shortage of basic
services like water, electricity, transport, public health, education, etc. Along with
thee, problems of migration and urbanisation are associated with the growing
population which further lead to the law and order problem. When faced with these
challenges, the state and other players can adopt appropriate measures to solve them.

3.3 Policy Formulation: Data relating to trends in population growth help planners in
formulating policies for economic plan of the country. Population data are also used
by planners to project future trends in fertility and formulate policy measures to
control birth rate. Demographic data also help in projecting labour force and the
number of people in dependent and productive groups in order to estimate the labour
force available for productive employment. This in turn will help in making estimates
regarding employment to be generated during the plan period.

3.4 Administrative Purpose: It helps administrators to run the government. In most

developing countries, almost all social and economic problems are associated with
population growth. The administrators have to find solutions to the problems arising
from the population growth.

3.5 Importance in the Political System: Census figures help in demarcation of

constituencies for election purposes. Political parties also help to find out from the
data the number of male and female voters, their levels of education, age structure,
level of earning etc. On these bases, political parties can raise issues and promise
solutions in their manifesto.

4 SOURCES OF DEMOGRAPHIC DATA

The sources of demographic statistics are the published reports, unpublished worksheets,
datasets, etc. that are produced by official or private agencies through a variety of media. The
sources may simply report primary statistics, or they may in addition include text that
describes how the statistics were obtained or an analysis that describes how valid or reliable
the statistics are deemed to be. These sources may also contain descriptive or inferential
material based in the statistics they contain.

If the statistics have been released as part of an electronic package or are available on the
internet, it is possible for the analyst to generate customised graphics, table or charts. The

4
same statistics may be selectively reproduced or rearranged in secondary sources such as
compendia, statistical abstracts, and year book. Other secondary sources that present some of
these statistics are journals, textbook and research reports.

Many important demographic statistics are produced by combining census and vital statistics.
Our interest will be census, sample surveys, and vital statistics.

4.1 Census: This is the “total process of collecting, compiling & publishing demographic,
economic and social data pertaining, at a specified time or times to all persons in a
country or delineated territory”.

Therefore, a population census is an official enumeration of the inhabitants of a country with

statistics relating to their location, age, sex, marital status, literacy status, language,
educational level, economic activity, number of children, migration, religion, citizenship,
ethnic heritage etc.

a) Methods of Population Census:

In the actual enumeration of the population, there are two ways to count people, namely;

De jure

De facto

De jure- under this method, the census covers the entire territory of the country and counts
persons according to their “usual” or “normal” place of residence in the country. The period
of enumeration ranges between 2-3 weeks and it is fixed. During this period, the enumerators
collect data from households by visiting them very often to fill up the various schedules.
Temporal residents at a place are not enumerated, except only permanent ones. This method
is also called “real” or “direct” enumeration method of census.

Advantages of de jure

i) The enumerators are given sufficient time to collect data from the households by
making frequent visits and this reduces on the errors.
ii) It is possible to collect a wide variety of data relating to sex, age, language,
education, occupation etc.

5
 iii) The diverse data are used by the census commission to arrive at various aspects of
population growth such as birth rates, deaths rates, sex ratios, occupational
distribution, literacy rate, etc.
iv) The data are used by administrators for policy formulation regarding health and
family planning, poverty alleviation, etc. Academics use them for research work.

Disadvantages

i) Non-permanent residents are usually left out.

ii) During the period of census, if the enumerator has filled up the census schedule of
a particular household on a specific date and a birth or death takes place there, this
will not be accounted for in the census. Similarly, the family may migrate to some
other place during the period.
iii) A problem may arise when a person has two houses at two different places and
resides in them for the purpose of business. This may lead o double counting.

b) De facto method: Under this method, the Census Commission fixes one date for
conducting the census throughout the country. It is usually done on a full moon night
because it is presumed that all households are present at their residence during that
time. Like de jure, the de facto enumeration covers the entire territory of the country
but counts each person in the population according to his/her geographical location on
the day of census undertaking.

Advantages:

i) Not time consuming since the entire enumeration work is done within one night.
ii) The households are actually present in their places of residence.

Disadvantages

i) Persons who are travelling during the night can not be enumerated.
ii) It requires large number of trained enumerators since the time period for enumeration
is fixed within one night. Trained personnel may not be available especially in
developing countries.
iii) The census work may not be completed and the staff may fill up the gaps arbitrarily
based on guess work. This arises because data are collected within only one day.

6
 Thus, the errors in the data tend to be very high and as such making planning for the
population impossible.
iv) Visiting households at night may be an inconvenience to the members. Hence, the
household may not provide accurate information to the enumerators.

Features of Census

i) Universality within a defined territory: Ideally, a national census should cover the
entire territory and all people resident or present. When these ideals are not
achieved for some reason (e.g., enemy occupation of part of the country in war
time, hostility of isolated tribe etc.), then the type of coverage attempted and
achieved should be fully described in the census publications.
ii) Simultaneity: A census is taken as of a given day. The canvas itself need not be
completed on that day, particularly on the case of de jure census. Often the official
time is mid-night of the census day. The more protracted the period of the canvas,
the more difficult it becomes to avoid omissions and duplications.
iii) Defined periodicity: The UN recommends that “census should be taken at regular
intervals so that comparable information is made available in a fixed sequence. A
series of census makes it possible to appraise the past, accurately describe the
present and estimate the future”. If the censuses are spaced 5 to 10 years apart,
cohort analysis can be carried out more readily and the results can be presented in
a more conventional terms. In the interest of international comparability, the UN
suggests that population censuses be taken as closely as feasible to the year ending
in “0”.
iv) Individual enumeration: the principle to be observed here is to list persons
individually along within their characteristics.
v) A household or family is treated as a unit. However, in large census operations,
migrant individual & homeless persons are also enumerated at night at their places
of rest or sleep.
vi) The census operations involve collection of data from households from door to
door by enumerators. In some countries, schedules are sent by post & the required
data are collected.
vii) Before starting the census operations, some preliminary steps are taken by the
Census Commission such as preparation of schedules, lists of households in each
area, training of enumerators, etc.

7
 Some problems of Census

i) Census is not a continuous process and it is usually conducted in an interval of 5 to

10 years. This means that there are no experienced staffs as it requires training of
new staff for each census exercise.
ii) The enumerators often interpret the terms used in the schedules in their own way
despite the guidelines supplied to them by the Census Commission.
iii) In the census operations, the enumerators are required to go from door to door to
collect data. This work is not only time consuming but also monotonous. Some
dishonest enumerators may fill up the schedules with false figures.
iv) Many persons are reluctant to provide correct information for fear that it may be
used for some other purposes. This happens if the household is illiterate or the
enumerator is not able to convince the former that the exercise data are kept secret
by law.
v) The household schedule pertaining to the census does not have any column about
the number of family members who might have gone abroad. This may lead to
under-enumeration.

4.2 Registration Methods: These pertain to the population’s demographic vital events
(births, deaths, and in some place, migration) and measure them as they occur.
Registration methods apply principally to birth and deaths, although many countries also
maintain registration of marriages, divorces, and abortion.

Strictly speaking, a population register is a list of persons that includes the name, address,
date of birth, and a personal identification number. Registration is a secondary source of
demographic data which is available from four sources, namely:

i) Vital registration
ii) Population Register
iii) Other records
iv) International Publications

8
 i) Vital Registrations: These are data derived from civil registration system as well
as from actual records of vital events. Recording of vital events (vital statistics)
such as births, deaths, marriages, divorces, etc. is obligatory on the part of every
citizen in a country. For example, the birth of a child has to be registered and the
occurrence of death is required to be registered. Such registration involves the
filling up of a proforma with the columns:
ii) Birth Certificate: Name, father’s name, mother’s name, age of father, age of
mother.
iii) Death Certificate: Name of the deceased, date of death, sex, race/caste/tribe, age
of the deceased, place of death, cause of death, occupation, marital status,
permanent residence, etc.

Advantage

The quality of vital events/ statistics are far better especially those in developed countries.

Disadvantage

i) It is expensive to conduct and maintain

ii) In most developing countries where the majority of people are illiterate and reside
in rural areas, births and deaths are not reported to the registration authorities. As
such, registration records remain incomplete and are imperfect source of
demographic data.
iii) The fact that the vital record is a legal document limits the amount and kind of
non-legal information that can be included in it.
iv) The method is affected by the number of and variety of persons involved in
registering the events. For example, the birth registration in some countries
requires actions by thousands or millions of individual citizens and hundreds of
local officials. Most of these people will have less training and expertise in data
collection than the enumerators who interview respondents in censuses or other
population survey. Enumerators are usually given intensive training in which the
importance, purpose and the exact specification of the information sought are
thoroughly explained.
v) If the legal functions are poorly performed, the statistical programme will suffer
because public pressures will demand that first priority be given to serving
people’s needs for copies of their personal records.

9
 4.1 DEMOGRPHIC MEASURES

These are the techniques applied to analyse population change. There are several of them,
including among others the following:

a) Balancing Equation
b) Ratios
c) Rates
d) Cohort

a) Balancing Equation:

In any time interval, population of a given country can increase of decrease as a result of
births, deaths, and migration (movements across a country’ boundaries). Births and migration
add to the population. If data are available from two censuses, and the numbers of births,
deaths, and in-and out migrants are known, then the equation must balance exactly, if all the
data are perfectly accurate.

Population Change=(Births-Deaths)+(Immigrants-Emigrants).

Pt=P0+(B-D)+(I-E)

Where: P0=Initial Population

Pt=Population after time t

The equation can split into two basic components:

Natural Increase=Births (B)-Deaths (D)

Net Migration=Immigration (I)-Emigration (E)

In almost all countries, natural increase is the most important component of overall
population change overtime. Each component of population change can be expressed as an
absolute number, or more commonly as a rate. A rate always has three components, namely;
numerator, denominator and a time period. The denominator for the calculation of an annual
rate is the estimated mid-year population. Demographic rates are ordinarily calculated per
1000 persons per year.

10
NB: For census evaluation purpose, there is a residual (e) needed to make the equation
balance exactly, expressed as:

P1=P0+(B-D)+(I-E)+e

“e” is referred to as the error of closure and represents the balance error in the data on births,
deaths, net migration, and the coverage of the two censuses

Interpretation

If “e” is 0, there is no error in the enumeration of P1.

If “e” is <0 (negative), P1 is under-enumerated relative to P0

If “e” > 0 (positive), P1 is over-enumerated relative to P0

Computational procedures of Population Balancing Equation:

a) Compile registered numbers of inter-censual births, death, and migrants. The data
sources are vital registration, immigration record system (residence permit, border
records etc.
b) Calculate the “expected”census population (E(P1))

E(P1)=P0+(B-D)+(I-E)

c) Calculate the residual error or error of closure

e=P1-E(P1)

Interpretation

i) If P0 has been adjusted to net coverage error, the estimated residual error (e) will
represent an estimate of net coverage error, in P1.
ii) If “e” is positive, P1 is over-enumerated
iii) If “e” is negative, P1 is under-enumerated.
iv) If P0 is not adjusted, “e” will represent an estimate of relative level of net coverage
error in P1 in comparison with P0.

Example of Sri-Lanka, 1971, 1981 censuses

11
 E(P1)=P0-B-D+M

12,849,796-3,716,878-1,002,108+(-446911)=15,117,655

e=P1-E(P1)

14,848,364-15,117,655

-269,291

Interpretation:

P1 is under-enumerated relative to P0

Limitations of Population Balancing Equation

i) Incomplete and defective data on components of population change are very common.
Thus, applicability of the methods is limited to countries with good vital registration
coverage and migration data.
ii) It is generally not useful for obtaining estimates of net census coverage error for sub-
national populations (for example, regions, provinces, etc.). In addition to the
components of population change considered, internal migration has to be taken into
account.
iii) For most practical purposes, the use of the population balance equation is limited to
analysis of net coverage error at the national level.

b) Cohort: This is the aggregate of all units that experience a particular demographic
event during a specific time interval. A cohort usually consists of people, but it may
also consist of entities (e.g, marriages) formed by a demographic event. The cohort is
normally identified verbally by the event itself and by the time period in which it is
experienced. A commonly used cohort is the “birth cohort”, and constitutes persons
born during the same period and will pass through life together.

Limitations

Computing cohort rates and probabilities requires complete information on each individual
until he/she has died or at least has ceased to be at “risk” of the event of interest. For

12
mortality, one has to wait until the last person of a birth cohort dies in order to complete
mortality indicators. For the case of fertility, one has to wait until the last woman of a birth
cohort reaches the end of her child bearing age (menopause).

Cohort Survival Ratios

i) (Intercensual) Cohort Survival Ratios (CSR)- this technique is based on a comparison

of the size of birth cohorts enumerated in successive censuses. In the absence of
census errors, the ratio of the number of persons in a cohort enumerated in the second
census should approximate the survival rate that would be expected on the basis of
mortality conditions. For example, assuming there was a cohort of males aged 40-44
at the time of the first census, say 2002. If the next census is to be held exactly 10
years later, in 2012, this cohort will be aged 50-54. In the absence of other factors,
one would expect their numbers to have reduced only by the life table quantity
10dx=lx-lx+n, i.e. the number of deaths to those aged x over the subsequent 10 years.

Limitations

i) The method is less useful when other factors make it difficult to determine
whether deviations from the expected CSR are due to census error or something
else.
ii) Substantial net migration (unless there are accurate estimates of net migration)
iii) Changes in the country border between censuses
iv) Differential census undercount.
v) Changes in the population groups included in the two censuses (e.g. active
military, nomadic groups) if the size of these groups is substantial

Calculating CSR

Steps:

i) Intercensual cohort survival rates are defined as:

n Px + a (t + a)
nCSR(a)=
n Px (t )

Where: t=time of first census

13
 a=Number of years between censuses

nPx(t)=Size of the cohort at the time of the first census

nPx+a(t+a)=Size of the cohort at time of the second census

ii) The ratio of the observed Intercensual Cohort Survival rate to the corresponding
survival rate:

n Px + a (t + a)
Px (t )
Rx = n
n
n Lx+a
n Lx

Where: nPx+a(t+a) = Size of the cohort at time of the second census

nPx=(t)=size of the cohort at the time of the first census

nLx+a=Life table number of person years lived in age interval x+a to x+a+n years

nLx=Life Table number of person-years lived in age interval x to x+n years.

Interpretation

i) In the absence of census error, the expected value of the ratio ( nRx) would be 1
(One)
ii) Ratio values of any particular cohort which exceed 1(One) would indicate over-
enumeration of the cohort in the second census relative to the first census.
iii) Ratio value less than 1 (one) would indicate under-enumeration of the cohort in
the second census relative to the first census.

Possible Bias

Discrepancies can arise due to 3 factors

i) Actual census errors

ii) Deficient data/adjustments for migration
iii) Wrong Life Table

14
5.1 AGE AND SEX COMPOSITION

Age: Is the most important variable in the study of mortality, fertility, nuptiality, migration
and other areas of demographic analysis. Age of an individual in a census is commonly
defined in terms of the age of the person at his/her last birthday. The UN defines age as “the
interval of time between the date of birth and the date of the census, expressed in completed
solar years”.

Sex: This is a genital tubercle when a child is born. Sex is normally fixed at birth. On
average, boys are born with penises ranging from 2.9 to 4.5 centimetres in length. For girls,
the clitoral length at birth ranges between 0.2 to 0.85 cm.

Importance of Ag and Sex

1) Planning: Many types of planning such as military planning, planning of community

institutions and services such as health services and planning of sales programmes
require separate population data for male and females and for age groups.
2) Age data are important for measuring potential school population, the potential
voting population and potential manpower.
3) Age data are required for preparing current population estimates and projections i.e.,
projection for households, school enrolment, labour force, teachers, health services,
food etc.
4) Social scientists need data on age and sex because social relationships within
community are affected by the relative number of males and females and the relative
number at each age.
5) Social roles and cultural patterns may be affected by the age and sex composition of a
population. For example, imbalances in the number of men and women may affect
marriage and fertility patterns, labour force participation and the sex roles within the
society.
6) Age data are important in the computation of the basic measures relating to the factors
of population change and the problem of economic dependency.

Quality of Age and Sex Data

Sex: In some countries misreporting of sex may occur. This may be due to the following
reasons:

15
 a) Parents may report males as females to avoid evil spirits.
b) Males may be reported as females to avoid military service.
c) Due to under-enumeration of certain sections of the population.

Age: The errors in reporting of age have probably been examined more intensively than the
reporting errors for any other question in the census. Errors in the tabulated data on age may
arise from the following types of errors of enumeration:

i) Coverage errors
ii) Failure to record age
iii) Misreporting of age

Coverage errors are of two types:

i) Individuals of a given age may have been missed out by the census.
ii) Erroneously included in it e.g. counted twice

The first type of coverage error represents gross under-enumeration at this age. The second
type represents gross over-enumeration. The balance of the two types of coverage errors
represents net under-enumeration at this age.

Note: Under-enumeration normally exceeds over-enumeration.

Besides, the ages of some individuals included in the census may:

Not have been reported,

Have been erroneously reported by the respondent,

Erroneously estimated by the enumerator,

Erroneously allocated by the census office

A complete census report of age in comparison with the true ages of the persons enumerated
would show the number of persons at each age for whom age was correctly reported in the
census, the number of persons incorrectly reported “into” each age from lower or higher ages,
and the number of persons incorrectly reported “out” of each age into higher or lower ages.
Such tabulations reflect what is referred to as gross misreporting of age, also known as
response variability of age.

16
If, however, one disregards the identity of individual allows for the offsetting effect of
reporting “into” and reporting “out of” given ages, one ends up with much smaller errors
based on comparison of reports for individuals. Such net-misreporting of characteristic is
called response bias.

The combination of net under-enumeration and net misreporting (response bias) for a given
age is termed “net census under-count” or “net census error”. It is termed as “net census over
count” if the number in age is over-stated.

For example, the group of people reporting age 42 in the census consists of the following:

i) Persons whose correct age is 42.

ii) Persons whose correct age is over or under 42 but who erroneously report 42.

The latter group is offset or wholly by;

iii) The number erroneously reporting “out of” age 42 into older or younger ages.

NB: The difference between ii and iii represents the “net misreporting error” for age 42. In
addition, the census count at age 42 is affected by net under-enumeration at this age i.e. by
the balance of the number of persons aged 42 omitted from the census and the number of
persons aged 42 who are erroneously included in the census.

It is important to note that the gross and net misreporting errors are smaller when data are
grouped into 5-year groups or broader groups than for single ages. This is because
misreporting of age within the broader intervals has no effect.

The amount of net under-enumeration accumulates and grows as the age interval widens,
because omissions tend to exceed erroneous inclusions at each age. For the total population,
the amount of net under-enumeration and the amount of net census undercount are the same
because net age misreporting balance out to zero over all ages.

The techniques for evaluating and analysing data on age and sex composition are related,
particularly those for evaluating and analysing age data. We shall look at the following major
areas:

1) Analysis of sex composition

2) Analysis of deficiencies in the Age Data
3) Analysis of Age Composition

17
 1) Analysis of sex composition

The measures of sex composition are few and they include the following:

a) The percentage of males in the population or the masculinity proportion

b) The sex ratio, or the masculinity ratio
c) The ratio of the excess or deficit of males to the total population.

a) The percentage of males in the population or the masculinity proportion

This is the measure of sex composition used in non-technical studies. It is expressed as:

Pm
* 100 ………………………………………………………………………….(1)
Pt

Where: Pm=Number of males

Pt=Total population

Interpretation: Fifty is the point of balance of the sexes. A higher figure denotes an excess
of males and lower figure denotes an excess of females.

Exercise: In the 1990 the population of males in Venezuela was 9,019,757 and the total
population was 18, 105,265. Use the figures to compute the masculinity proportion.

9,019,757/18,105,265=49.8%

The value of 49.8% implies there were more females enumerated during the census.

b) Sex Ratio

This is the measure of sex composition and it is used in technical studies. It is defined as the
number of males per 100 female. It is expressed as:

Pm
* 100 ……………………………………………………………………………..(2)
Pf

18
Where:

Pm=Number of males

Pf=Number of females

Interpretation: One hundred is the point of balance of the sexes. A sex ratio above 100
denotes an excess of males and a figure below 100 denotes excess of females.

Exercise: Assuming the census carried out in Uganda in 2012 had 45,098,071 people with a
total of 21,879012 males. Calculate the sex ratio of the population. What observation would
you make?

Note: Sex Ratio is a more sensitive indicator of difference in sex composition because it has a
relatively smaller base.

c) The Excess (deficit) of males as a percentage of the total populations:

This is expressed as:

Pm − Pf
* 100 ……………………………………………………………………(3)
Pt

Exercise: Use the figures provided for the Uganda population census results to compute the
Excess or deficit of males as a percentage of the total population.

Interpretation: The point of balance is zero. A positive value denotes an excess of males and
negative value denotes an excess of females.

Sometimes it is desired to convert the masculinity proportion into the sex ratio or the
percentage excess or deficit of males or the reverse, in the absence of the basic data on the
numbers of males and females. The formulae below are used:

Sex Ratio
Masculinity proportion= * 100 ………………………………………..(4)
1 + Sex Ratio

Masculinit y Pr oportion
Sex Ratio= * 100 ………………………………………..(5)
1 − Masculinit y Pr oportion

Percentage excess or deficit of males

19
 = [ Masculinit y proportion − (1 − Masculinit y Pr oportion)] * 100 ………………….(6)

Exercise the census figures provided for Venezuela and use the above formulae to calculate
the percentage excess or deficit of males.

Sex Ratio
Masculinity proportion= * 100 =(0.9928/1.9928)*100
1 + Sex Ratio

Masculinit y Pr oportion
Sex Ratio= * 100 =(0.4982/1.0.4982)*100
1 − Masculinit y Pr oportion

=(0.4982/0.5018)*100

=99.8

Percentage excess or deficit of males

= [ Masculinit y Pr oportion − ( Masculinit y Pr oportion )] * 100

=[0.4982-(1-0.4982)]*100

=(0.4982-0.5018)*100

= -0.0036*100

=0.4 per cent

2) Analysis of Deficiencies in Age Data: We shall consider the following:

a) Errors in single years of age
b) Errors in grouped data
c) Reporting of extreme old age
d) Failure to report age

Errors in single years of age: The tendency of enumerators or respondents to report certain
ages at the expense of others is called age heaping, age preference or digital preference. Digit
preference refers to preference for the various ages having the same terminal digit. Age
heaping is most pronounced among populations or population sub-groups having a low
education. It is the principal type of error in single-year-of-age data, although single years are
also affected by other types of age misreporting, net under-enumeration, non-reporting or
mis-assignment of age. Age “0” is under-reported often. This is mainly because two major
reasons, namely:

20
 “0” is not regarded as an age by many people

Parents may tend not to think of new born infants as regular members of the
household.

Causes of errors in Age Data:

Are reporting suffers from a number of errors due to a number of causes. The reasons may
vary but the causes can be classified as follows:

i) Ignorance of correct age

ii) Carelessness in reporting and recording
iii) A general tendency to state age in figures ending in certain preferred digits.
iv) A tendency to exaggerate length of life at advanced ages
v) Mis-statement arising from motives of an economic, social, political or purely
personal character.

The causes of age mis-reporting are common to most demographic investigations. In sub-
Saharan Africa, these causes are reinforced by the fact that in almost all African cultures,
numerical age has had no importance over the years. A good part of the errors in age data in
African censuses and survey arise from this factor. As a result, the age-sex distributions of
populations in many African countries show the following irregularities:

• Deficiencies in the number of infants and young children

• Heaping at ages ending in 0 and 5, hence a relatively large concentration of persons
enumerated with ages ending in 0 and 5.
• A preference of even ages over odd ages, hence a relatively large concentration of
persons enumerated with even numbered ages.
• Unexpectedly large difference between the frequency of males and females at certain
ages.
• Unaccountably large differences between the frequencies in adjacent age groups.
• Non-stated or unknown ages

21
Methods for Detecting Errors in Age Data

Essentially, there are two broad approaches to the problem of identifying possible errors in
age data, namely;

a) Case-by-case checking Techniques. This involves employing data from interviews

and independent lists or administrative records. This is done before the data are
published.
b) Use of techniques of demographic analysis. This where we shall dwell on in our
discussions.

Almost all the techniques succeed in identifying some of the errors in the age data, but a few
of them go further to suggest methods of correcting such errors when detected.

i) Age Ratios, Sex Ratio, and Age/Sex Accuracy Index.

Age Ratio is the ratio of the population in the given age group to one half of the population in
the adjacent age groups. Age Ratio and Sex Ratios can be use either separately or jointly in
evaluating the quality of the census returns or survey by age groups. Age Ratio is expressed
as.

Px
Age Ratio = 5
* 100 ………………………………………………(1)
1 / 2( 5 Px −5 + 5 Px +5 )

Where:

5Px=Age group from age x to x+5,

5Px-5=Preceding age group

The age ratios are usually calculated for males and females separately and can be calculated
for each age group (except for the youngest and the oldest) provided the intervals are equal.

Interpretation:

• The computed age ratios are compared with the expected value, usually 100.
• An overall measure of the accuracy of an age distribution (called an Age Accuracy
Index) is derived by taking the average deviation (regardless of sign) from 100 of the
age ratios and summing overall age groups. The lower this index the more adequate
the census data on age.

22
 • An Age Ratio under 100 implies either that members of the group were selectively
under-enumerated or that errors in age reporting resulted in mis-classifying persons
who belonged to the age group.
• A ratio of more than 100 suggests the opposite of one or the other or both of above
conditions i.e., members of the age group were over-enumerated, including persons in
the age group or both.

Note: Age specific sex ratios (number of males per 100 females in each age group) can also
be used in evaluating census age data. The general pattern of the age-specific sex ratios is
such that they approximate to the sex ratio at birth in the younger ages, and fall gradually
with advancing age.

Zelnik Method

This assumes that age is curvilinearly related hence the decision to take the average of the
three populations surrounding the age group with the age group itself inclusive.

= nP x x 100

1/3 (nP x –n + 2nP x + nPx + n)

Ramachadran Method:

If there is a preferred digit, Zelnik assumption will not hold. It therefore alters the formula by
multiplying the central age by 2.

= nP x x 100

1/4 (nP x –n + 2nP x + nPx + n)

Any discrepancy observed in each age group is the measure of net age misreporting.

Age Specific Sex Ratio is expressed as:

Pxm
5
f
* 100 …………………………………………………………………(2)
5 Px

The Table below depicts the numbers of men and women per age group. Use the Age and Sex
Ratios to detect the level of errors in the age data.

23
 An extract from the Uganda population census results
depicting the male & female populations per age group

Age Males Females

0-4 643041 654258
5-9 515520 503070
10-14 357831 323460
15-19 275542 265534
20-24 268336 322576
25-29 278601 306329
30-34 242515 245883
35-39 198231 179182
40-44 168937 145572
45-49 122756 95590
50-54 96775 81715
55-59 59307 48412
60-64 63467 54572
65+ 113185 100392

Indexes Based on Rectangularity

The indexes to be used depend on the assumptions made. The simplest device is the one
based on rectangular distribution where we the assumption of equal numbers in each age is
made over some age range which included and preferably centred on the age being examined
for examples a population in ages 39, 40 and 41 denoted by p39, p 40, and p 41 may be used to
examined preference for age 40.

If in certain year, preference for age 40 is to be determined based on the assumption of

rectangularity of population distribution. This can be calculated as the ratio of population 40
into 1/3 of population ages 39, 40, and 41 expressed in percentages. This is for 3 years age
range.

P 40
i. X 100
1 ( 39+ P 40+ P 41)
P
3

If 5 year age range is used it will therefore be expressed thus.

P 40
= X 100
5 ( P38 + P39 + P40 + P41 + P42 )
1

e.g Population of Philippines in 1960 for the 3 year age range

24
 P 40
= X 100
1 ( 225,207 + 434,156 + 126,632)
3

434.156
= x 100 = 165.71
3 (785,995)
1

Where as for 5 years age range

P 40
= X 100
5 (316,210 + 225,207 + 434,156 + 126,632 + 17,881)
1

434.156
= x 100 = 164.44
5 (1,320,086)
1

The higher the index the higher the concentration. Index of 100
indicates no concentration.

Whipple’s Index:

This is another measurement of age heaping. This index has been developed to reflect
preference for or avoidance of a particular digit. For a large age range, the assumption about
true form of distribution may be that of linearity i.e where true figures formed an arithmetic
progression or where they decrease by equal amount form age to age over the age range.

The whipples index is one of the indexes where assumption of rectangularity or linearity is
made. If the assumption of rectangularity is made in 10 year age range, the heaping on
terminal digit zero in the age range 23 to 62 years may be measured by comparing the sum of
the populations at the ages ending in zero in this age range 23-62 with 1/10th of the total
population in the age range.

For example all ages ending in zero will be P30 + P40 + P50 + P60 comparing with 1/10 th of
summation of P23 to P62 i.e P23 + P24 …… + P62 multiply by 100.

P
= 30 + P40 + P50 + P60 X 100

1/10 th ( P23 + P24 + P25 + …….+ P60 + P61 + P62

For ages ending 0 i.e ten year age range

62

 23
P
aendingin 0
= 62
X 100
1 10 a P

23

25
In the same manner, employing the assumption of rectangularity or of linearity in a 5 yr age
range, heaping on terminal digit 0 and 5 combined in the age range 23-62 may be measured
by comparing the sum of the population at ages in this range ending in zero and five with 1/5
of the total population in the age range.

= P
25 + P30 + P35 +….+ P 55 + P60 X 100

1/5th ( P23 + P24 + P25 + …….+ P60 + P61 + P62

For ages ending 0 i.e ten year age range

62

 23
P
aendingin '0' or 5
= 62
X 100
1 5 a P

23

ASSUMPTIONS

1. Assumption of rectangularity or majorly linearity in age distribution

2. Assumption that age heaping are recorded only in ages ending in ‘0’ and ‘5’

3. Assumption that population is close in migration or are equally affected by migration

at all ages

4. Assumption that population distribution is not affected by unusual occurrences.

5. Assumption that population of those at the ages of childhood and those at extreme old
ages are affected by other types of errors other than by preference for specific
terminal digits

e.g

Population of Turkey

Age Male Female (‘000’)

(‘000’)
25 191 393
30 301 471
35 283 373
40 244 409
45 201 260
50 158 350
55 78 150

26
 60 121 297
Population of ages ending in ‘0’ 824 1,527
Population of ages ending in ‘5’ 753 1,176
Population of ages ending in ‘0’ and ‘5’ 1,577 2703

….Whipples Index

For males age ending 0

= 301+244+158+121 X 100

1/10 (3,601)

= 824 X 100

360.1

= 228.8 or 299

For the females age ending in 0 = 386.5822785 ≈ 387

For the males ages ending in 5 = 209

For females age – ending in 5 = 1,176 x 100 = 297.72 or

298

1/10 (3,601)

The females have the higher tendency to concentrate on ages ending in 0 and 5 than males.

This may be due to

1. High illiteracy rate among females

2. They are less interested in age most especially in the traditional set up.

3. Males in most cases report the age of females on their behalf and there is tendency to
use rounded figures for females

Note: Whipples index deals with measuring heaping of digits ending in zero and five only.

The heaping varies from 100 showing no preference for digit ending in zero or five to 500
showing that only digits ending in zero or five were reported.

27
LIMITATIONS

i. Whipples Index is applicable only where age is reported in single

years.
ii. The choice of age range 23 to 62 is largely arbitrary. It is based on
Whipple cultural setting. The ages of childhood and extreme old age
according to whipples are often excluded since it is believed to be
more affected by other types of errors than by preference for specific
terminal digit.
iii. The assumption of rectangularity or linearity in age distribution is less
applicable in a real situation. Age distribution of population is not
rectangular.
iv. It does not take into consideration that age distribution may be affected
by unusual occurrence – baby boom, war flood disaster and famine.
v. It does not take care of mortality.
vi. Some demographers are of the views that whipples index are not
efficient method of age preference since it measures heaping on ages
ending in 0 and 5 only.
The method could however be extended to other digits but whipples
measure only ages ending in ‘0’ or ‘5’.

ADVANTAGES

i. it is very easy to calculate

ii. It can be easily compared among population of various countries
Scale of Reliability
Quality of the data - Whipples Index
Highly Accurate - less than 105

Fairly Accurate - 105 -109.9

Approximate - 110 -124.9
Rough - 125 – 174.9
Very Rough - 175+
Myer’s Blended Index

28
Myers index is an ingenious device, which reflects the preference or the dislikes for each of
the ten digits 0,1,2,3,4,5,6,7,8 & 9. It is applicable where age is given in single years. The
method is called blended because e it was developed to avoid the bias in indexes calculated,
in the manner the whipples index was done due to the fact that numbers ending in zero would
be larger than numbers ending in 1 & 9.

The Underline Assumptions

a. It assumes that ages are linearly related.

b. It assumes the likelihood for age heaping (or avoidance) in each age group.

c. the Myers method assumes that in the absence of systematic irregularities in the
reporting of age, a blended sum at each terminal digit should be approximately equal to the
10% of the total blended population.

If the sum of any given digit exceed 10% of the total blended population, it indicates over
selection of ages ending in that digit i.e digit preference. On the other hand, a negative
deviation or sum less than 10% of the blended total indicates under selection of ages ending
in that digit i.e digit avoidance.

Unlike whipples index which is restricted to ages 23-62, Myers is computed to the nearest 9.
However the starting point is age 10 but the terminal point will be the nearest 9 to the highest
age given e.g. for age 10-75, the method will cover 10-69, where it is up to 90 years the
method will cover 10-89.

Data Requirements

Population distribution by single year of age within age range 10-69 or 10-79 or in some
cases 10-89 from census data.

Procedure of Calculating Myers Index

Step 1: Sum the population ending in each digit over the whole range
starting with the lower limit of the range of population
distributed in single years up to 89 (i.e. 10-89)

Sum (10,20,30,….80)

Sum (11,21,31,….81)

29
 Sum (19,29, 39,49,…..89)

Step II: Sum up the population excluding the first population combined
in step I e.g

Sum (20,30,40,….80)

Sum (,21,31,41,….81)

Sum (,29, 39,49,…..89)

i.e ages 10,11,12,23,…. 19 are excluded

Step III: Weight the sum in steps I & II to obtain blended population on
each terminal digit and add the result to obtain Grand blended
population

Weight (W)

1 and 9 for the ‘0’ digits

2 and 8 for the 1 digits

3 and 7 for the 3 digits

….

….

10 and 0 for the 9 digits

Step IV: Convert the distribution is Step III into percent.

Step V: Take the deviation of each percent in step IV from 10.0. The
value for each terminal digit is expected to be zero (0) after
taking the deviation.

30
 The result in step IV indicates the degree of preference or avoidance of
age in each terminal digit.

Bi = Blended Population i range from 0-9

9
Grand Blended Population =  Bi
i =0

 
 Bi 
Magnitude of Preference =  9 x100
 Bi 
 
i =0

−10

A summary index for preference for all terminal digits known as Myer
Blended meth or index is taken as ½ the sum of the deviations from 10% each
taken without regard to sign ½ the sum of magnitude of preference.

 
 Bi
9 
Myers Blended  Bi  9 x100 − 10%
 Bi 
 
i =0

i =0


The Myers Blended index is an estimate of the minimum proportion of persons in population
for whom an age with an incorrect final digit or terminal digit is reported. Theoretically, the
range of the index is between 0 and 90. While zero ‘0’ represent heaping, 90 represent the
reporting of all ages at a single digit.

Population of the Philippines by single years of age: 1960.

Age Number Age Number Age Number

Total 27,089,685 31 yrs 222,086 63 yrs 40,154
Under 1 year 786464 32 yrs 318,481 64 yrs 34,381
1yr 888,180 33 yrs 246,260 65 yrs 102,440
2yrs 963,230 34 yrs 233,700 66 yrs 26,445
3 yrs 969,309 35 yrs 401,936 67 yrs 35,311
4 yrs 965,232 36 yrs 242,659 68 yrs 40,711
5 yrs 957,698 37 yrs 242,462 69 yrs 20,921
6 yrs 928,673 38 yrs 316,210 70 yrs 136,771
7 yrs 938,899 39 yrs 225,207 71 yrs 13,000
8 yrs 841,636 40 yrs 434,156 72 yrs 28,017
9 yrs 702,492 41 yrs 126,632 73 yrs 16,662
10 yrs 841,356 42 yrs 217,881 74 yrs 14,490

31
11 yrs 581,400 43 yrs 169,167 75 yrs 50,558
12 yrs 796,786 44 yrs 151,142 76 yrs 15,010
13 yrs 619,293 45 yrs 319,118 77 yrs 11,878
14 yrs 596,592 46 yrs 160,329 78 yrs 23,353
15 yrs 565,714 47 yrs 160,855 79 yrs 9,212
16 yrs 566,942 48 yrs 237,287 80 yrs 73,741
17 yrs 538,891 49 yrs 155,094 81 yrs 5,532
18 yrs 651,318 50 yrs 313,636 82 yrs 9,331
19 yrs 491,441 51 yrs 78,534 83 yrs 5,653
20 yrs 565,801 52 yrs 128,935 84v 5,089
21 yrs 494,895 53 yrs 93,279 85 yrs 18,604
22 yrs 515,823 54 yrs 95,715 86 yrs 4,803
23 yrs 456,892 55 yrs 163,093 87 yrs 5,617
24 yrs 425,212 56 yrs 87,754 88 yrs 4,388
25 yrs 522,203 57 yrs 71,828 89 yrs 4,000
26 yrs 358,549 58 yrs 93,049 90 yrs 57,111
27 yrs 376,221 59 yrs 72,206
28 yrs 395,766 60 yrs 275,436
29 yrs 300,610 61 yrs 31,299
30 yrs 535,924 62 yrs 49,634

|0| whipples index is from 23-62

32
Calculation of preference indexes for Terminal

Digits by Myers Blended index for the Philippines 1960

Population with Weight for Blended population Deviation of

Terminal terminal digit ‘a’ present 10.0
digit ‘a’ Starting at Starting at Col. 1 Col. 2 No. (1) x (3) + Percent col 6-10.0
age 10 age 20 (2) x (4) Distribution
+’a’ +’a’
(1) (2) (3) (4) (5) (6)
0… 3,176,821 2,335,465 1 9 24,196,006 16.06 +6.06
1… 1,553,378 971,978 2 8 10,882,580 7.22 -2.78
2… 2,064,888 1,261,102 3 7 15,071,378 10.00 -
3… 1,647,360 1,028,067 4 6 12,757,842 8.47 -1.52
4… 1,556,321 959,729 5 5 12,580,250 8.35 -1.65
5… 2,143,666 1,577,952 6 4 19,173,804 12.72 +2.72
6… 1,462,491 895,549 7 3 12,924,084 8.58 -1.42
7… 1,443,063 904,172 8 2 13,352,848 8.86 -1.14
8… 1,762,082 1,110,764 9 1 16,969,502 11.26 +1.26
9… 1,278,691 787,250 10 0 12,786,910 8.49 -1.51
TOTAL 150,695,204 10.00 20.07
Summary = Total 10.04
Index of Index
age 2
Preference

Note: A summary index for preference for all terminal digits can be taken as ½ the sum of
the deviation from 10.0% each taken without regard to sign thus ½ (20.07) = 10.04

For the population of Philippines examined, the summary of preference is 10.04. This
indicates heaping by the heaping is not a serious one hence it could be said that the
population is moderately reported. Very small deviations from 100 or 10 or 0 shown in
various measures of heaping don’t necessarily indicate heaping and they should be
disregarded.

Limitations

i. The assumption that preferences for all digits are the same is not always true.
This ‘actual’ or ‘true’ population in any single year of age does not exactly
equal 1/5 or 1/10 of the five and ten year age groups respectively.
ii. The assumption that age distributions of population are linearly related may
not be a reality. Age distribution of population may have irregular
fluctuations depending largely on the past trend of births and deaths. The digit

33
 preference cannot be measured precisely as distinctions between the errors due
to digit preference, other factors and real fluctuations can hardly be made.
iii. The method as may be observed does not cover the entire age range.
iv. Beside the method can only be applied only where ages are presented in single
years.
v. It does not identify error of compensation.
vi. Myers index can produce different results because the age at which the
calculation starts or ends may vary.
vii. The method also does not take care of coverage error but centres only on
content error i.e. error of misreporting.
Usefulness

i. Above notwithstanding, Myers index is one of the widely applied methods of

measuring age preference at each digit.
ii. It assists in measuring the accuracy of data.
iii. It also facilitates comparison among different population, more so, when the
same age range is used in the calculation.
iv. It is also very good method of measuring differentials in digit preference by
sex.
v. The method helps in selecting five-hear age grouping that can be used to
minimize errors.
Horizontal Method of Analysis

Sex Ratio

Sex Ratio can be calculated for single years of grouped data. Sex ratio is the
number of males per hundred females.

M x 100

1991 Population Census

Sex Ratio = 759,986 x 100

For Ekiti State 775,804

34
 = 97.96

Sex Ratio at Birth

This is expressed as the number of male births to a hundred females births.

= PBM x 100

PBF

ASSR is the number of males per hundred females in a particular age group

ASSR = 5Pmx x 100 where x = 10

5Pfx

= Pm10 - 14 x 100

Pf10-14

= 5,812,538 x 100

5,336,143

= 108,95

ASSR can be used in evaluating census age data. The general pattern of age specific sex

Ratio is such that it approximate sex ratio at birth in younger ages and then decline gradually
as it tends towards advance ages.

Where we have similar sex ratio at birth, ASSR are usually the same where migration is not
considered. It should however be noted that mortality is affecting sex ratio at older ages.
More women survived than men especially after child bearing.

POPULATION PROJECTION AND FORECAST

Population projection is trying to determine what the future population will be like. It
involves trying to forecast what will happen. Sometimes the term projection is used to
describe a predicted population. It is better to restrict the term projection to describe the

35
method or technique. The term forecast is used to indicate the actual predictions about which
demographers feel reasonably confident or projections which only go a few years into the
future.

Importance of Population Projection and Forecast

Population projections & forecasts are important because of some of the following reasons:

a) Local education authorities need forecast of the number of children for whom school
places will be required in the five or ten years. For case of Uganda, such forecast will
be required for regions or districts.
b) National forecasts are needed to enable the future demand for food, power, transport
and other services to be estimated.
c) Forecasts of the future age structure are required for the national insurance purposes,
since contribution rates are linked to the ratio of non-working to working people.
d) Forecast of the numbers of people classified by marital condition may be required to
estimate the future number of households, the potential membership of the workforce,
and the need for social security benefits.
e) Forecasts are made of number of students in higher education that help government
decide the proportion of the available public funds be allocated to universities.
f) Etc.

Approaches to Population Projection

There are two methods of carrying out population projection in common use. They include:

a) Mathematical method
b) Component method

Mathematical method: This is where the evolution of the population is assumed to be

described by dome fairly simple mathematical formula. Because of this, it I sometimes called
the formula method. This method is quick, simple and requires little in the way of data. It is
the approach of choice for many projections of the whole populations of the countries.

The component method: This where the components of population change are taken into
account explicitly. This method is much more cumbersome and has heavy data requirements.
It is more time-consuming but the advent of computers has made it a great deal quicker than

36
it used to be. It has the great advantage over the mathematical method that detailed aspects of
the population structure can be forecast.

The choice of the method depends on the degree of detail required in the projection. For some
purposes, only population size is needed; for others the population structure in five-year age
& sex groups may be necessary; occasionally very detailed projections (e.g., of the
population structure by single years of age & marital status) may be desired. These
requirements dictate the degree of disaggregation required in the model for population
change.

Often it is not possible to obtain the desired detail. This might be because the necessary data
are not available or are unreliable; it might be because the resources required to carry out the
projection are out of all proportion to its value; it might also be because the time taken to
produce the projection would render it useless by the time it was finished. The choice of
method and the degree of detail with which the chosen method is applied are influenced by
all these considerations.

The general procedures

37