Chapter 4: Census and Sample Investigation

4.0. Introduction
This unit explains the nature of sampling and how to determine the appropriate sample design. In
fact, sampling is common in daily activities, but most of these samples are not scientific. This
unit discusses the concept of sampling and the sampling process as a central aspect of economic
Sampling is defined in terms of the population to be studied. A population, or universe, is any
complete group of people, companies, colleges or the like that share some set of characteristics.
When a distinction is made between population and universe, it is on the basis of whether the
group is finite (population), or infinite (universe).
4.1. Difference between Census and Sampling
Definition of Census
A well-organized procedure of gathering, recording and analyzing information regarding the
members of the population is called a census. It is an official and complete count of the universe,
wherein each and every unit of the universe is included in the collection of data. Here universe
implies any region (city or country), a group of people, through which the data can be acquired.

Under this technique, the enumeration is conducted about the population by considering the
entire population. Hence this method requires huge finance, time and labour for gathering
information. This method is useful, to find out the ratio of male to female, the ratio of literate to
illiterate people, the ratio of people living in urban areas to the people in rural areas.

Definition of Sampling

We define sampling as the process in which the fraction of the population, so selected to
represent the characteristics of the larger group. This method is used for statistical testing, where
it is not possible to consider all members or observations, as the population size is very large.

As statistical inferences are based on the sampling observations, the selection of the appropriate
representative sample is of utmost importance. So, the sample selected should indicate the entire
universe and not exhibit a particular section. On the basis of the data collected from the
representative samples, the conclusion is drawn from the whole population. For instance: A
company places an order for raw material by simply checking out the sample.

Compiled Note For Research Method In Economics Page 1

The units which constitute sample is considered as „Sampling Units‟. The full-fledged list
containing all sampling units is called „Sampling Frame‟.

Census and sampling are two methods of collecting survey data about the population that are
used by many countries. Census refers to the quantitative research method, in which all the
members of the population are enumerated. On the other hand, the sampling is the widely used
method, in statistical testing, wherein a data set is selected from the large population, which
represents the entire group. Census implies complete enumeration of the study objects, whereas
Sampling connotes enumeration of the subgroup of elements chosen for participation.

Figure 4.1: Census and Sampling

The paramount differences between census and sampling are discussed in detail in the given
below points:

1. The census is a systematic method that collects and records the data about the members
of the population. The sampling is defined as the subset of the population selected to
represent the entire group, in all its characteristics.
2. The census is alternately known as a complete enumeration survey method. In contrast,
sampling is also known as a partial enumeration survey method.
3. In the census, each and every unit of population is researched. On the contrary, only a
handful of items is selected from the population for research.
4. Census, is a very time-consuming method of survey, whereas, in the case of sampling, the
survey does not take much time.
5. The census method requires high capital investment as it involves the research and
collection of all the values of the population. Unlike sampling which is a comparatively
economical method.

Compiled Note For Research Method In Economics Page 2

 6. The results drawn by conducting a census is accurate and reliable while there are chances
of errors in the results drawn from the sample.
7. The size of the sample determines the probability of errors in the outcome, i.e. the larger
the size of population the less are the chances of errors and the smaller the size; the
higher are the chances of errors. This is not possible with census as all the items are taken
into consideration.
8. Census is best suited for the population of heterogeneous nature. As opposed to sampling
which is appropriate for homogeneous nature.

The table below summarizes the difference between census and sampling

Table 4.1: Difference between sampling and census

Basis for Census Sampling

Comparison
Meaning A systematic method that collects and Sampling refers to a portion of the
records the data about the members of population selected to represent the
the population is called Census. entire group, in all its characteristics.
Enumeration Complete Partial
Study of Each and every unit of the population. Only a handful of units of the
population.
Time required It is a time consuming process. It is a fast process.
Cost Expensive method Economical method
Results Reliable and accurate Less reliable and accurate, due to the
margin of error in the data collected.
Error Not present. Depends on the size of the population
Appropriate for Population of heterogeneous nature. Population of homogeneous nature.

4.2. Sampling
The process of sampling involves a procedure that uses a small number of items or parts of the
whole population to make conclusions regarding the whole population.

Sample is a subset, or some part of a population.

Population or universe is a complete group of people, companies, college students, etc.

population (finite), and universe (infinite).

The purpose of sampling is to enable researchers to estimate some unknown characteristics of the
population.

Population element/unit: refers to an individual member of the population.

Compiled Note For Research Method In Economics Page 3

Census: is an investigation of all the individual elements that make up the population i.e. total
enumeration.

Why Sample? In a scientific study, when the objective is to estimate an unknown population
value, why should a sample be taken rather than a complete census? Sampling cuts costs, reduce
labor requirements, and gathers information quickly. Samples, if properly selected are accurate
in most cases. When the population elements are homogenous, samples are representative of the
population. Samples are accurate only when researchers have taken care to draw representative
samples properly.

4.3. Practical Sampling Procedures

Researchers must make many decisions before a sample is taken. Exhibit 4.1 presents these
decisions as a series of interrelated stages, even though the order of decisions does not always
follow this sequence.

Defining the Target Population

After the decision to sample has been made, the first question in sampling is to identify the target
population – which is the specific, complete group relevant to the research project. What is the
relevant population? The suitable population element may be the household or organizational
unit. It is important to define the target population (at the beginning), so that the proper source
from which the data are to be collected. Answering questions about the characteristics of the
population is the usual technique for defining the target population. For instance, the question "to
whom do we want to talk?" must be answered.

Exhibit 5.1 Stages in Selection of a Sample

Compiled Note For Research Method In Economics Page 4

To implement the sample in the field, tangible characteristics should be used to define the
population. In defining a population as all woman who are still capable of bearing children (for
instance 0, a more specific operational definition would be women between the ages of 12 and
50.

The Sample Frame

A sampling frame – is a list of elements from which a sample may be drawn, also known as the
working population. For instance, a sampling frame might be a list of all members of the
Ethiopian Economic Association. If a list of population is not available, materials such as maps
or aerial photographs may be used as a sampling frame. Some sampling services or list brokers
(firms) specialize in providing mailing lists or database that includes the names, addresses, phone
numbers, and e-mail addresses of specific population.

Simply, a sampling frame is the source material or device from which a sample is drawn.It is a
list of all those within a population who can be sampled, and may include individuals,
households or institutions. Sample Frame consists of a listing of all possible Sampling Units.

Sampling frame error: a sampling frame error occurs when certain sample elements are excluded
or when the entire population is not represented in the sampling frame. By error the sampling
frame may include elements that are not member of the ideal target population or some of the
elements of the ideal target population are not listed in the sampling frame. So there is the
probability of taking sample from outside the target population.

Figure 4.2: Sampling error

Compiled Note For Research Method In Economics Page 5

Sampling Units
During the actual sampling process, the elements of the population must be selected according to
a certain procedure. The sampling unit is a single element or group of elements subject to
selection in a sample (a member of a household).

Significance
Significance is the percent chance that a relationship found in the data is just due to an unlucky
(unsuccessful) sample, and if we took another sample we might find nothing. That is,
significance is the chance of a Type I error: the chance of concluding we have a relationship
when we do not. Social scientists often use the .05 level as a cutoff: if there is 5% or less chance
that a relationship is just due to chance, we conclude the relationship is real (technically, we fail
to accept the null hypothesis that the strength of the relationship is not different from zero).
Significance testing is not appropriate for non-random samples or for enumerations/censuses.
We would like to make similar inferences for non-random samples, but that is impossible. Any
relationship, not matter how small, is a true relationship (barring measurement error) for an
enumeration.

Confidence interval
Confidence intervals are directly related to coefficients of significance. For a given variable in a
given sample, one could compute the standard error, which, assuming a normal distribution, has
a 95% confidence interval of plus or minus 1.96 times the standard error. If a very large number
of samples were taken, and a (possibly different) estimated mean and corresponding 95%
confidence interval was constructed from each sample, then 95% of these confidence intervals
would contain the true population value, assuming random sampling.

4.2.1. Types of Sampling Techniques

The major alternative sampling techniques may be grouped into probability techniques and non-
probability techniques. In probability sampling every element in the population has a known
non-zero probability of selection. The simple random sample is the best-known probability
sample, in which each member of the population has an equal probability of being selected. In
non-probability sampling the probability of any particular member of the population being
chosen is unknown. Non probability sampling is a sampling technique in which units of the
sample are selected on the basis of personal judgment or convenience (arbitrary).

Compiled Note For Research Method In Economics Page 6

4.2.1.1. Probability Sampling
All probability samples are based on chance selection procedures. Randomness is a characteristic
of a procedure whose outcome cannot be predicted because it is dependent on chance. The
procedure of randomization (scientific) is the basis of all probability sampling techniques. The
probability sampling includes the following.

A) Simple Probability Random Sampling

Simple random sampling is a sampling procedure that makes certain that each element in the
population has an equal chance of being included in the sample. When population consists of
large numbers of elements, tables of random digits are used for sample selection.

B) Systematic Sampling
Systematic sampling is a sampling procedure in which an initial starting point is selected by a
random process, and then every nth number on the list is selected. Suppose a researcher wants to
take a sample of 1000 from a list consisting of 200,000 names of companies. With systematic
sampling, every 200th name from the list would be drawn.

C) Stratified Sampling
Stratified sampling is a probability sampling procedure in which simple random sub-samples are
drawn from within different strata that are equal on some characteristics.

The first step, for both stratified and quota sampling, is choosing strata on the basis of existing
information, such as classifying retail outlets on the basis of annual sales volume. In the second
step (the process of selecting sampling units within the strata), a sub-sample is drawn using
simple random sampling within each stratum. More efficient sample, Random sampling error
will be reduced with the use of stratified sampling.

A researcher selecting a stratified sample will proceed as follows:

(1) A variable is identified as an efficient basis for stratification. The stratification

variable is the categorized variable.
(2) For each separate sub-group or stratum, a list of population elements must be
obtained.

Proportional stratified sample is a stratified sample in which the number of sampling units
drawn from each stratum is in proportion to the population size of that stratum. The number of

Compiled Note For Research Method In Economics Page 7

sampling units drawn from each stratum is in proportion to the relative population size of the
stratum.

Disproportional stratified sample is a stratified sample in which the sample size for each stratum
is allocated according to analytical considerations. That is, sample size for each stratum is not
allocated in proportion to the population size.

D) Cluster Sampling
Cluster sampling is an economically efficient sampling technique in which the primary sampling
unit is not individual element in the population but a large cluster of elements (cities). The area
sample is a popular type of cluster sample. Area sample is a cluster sample in which the primary
sampling unit is geographical area. Clusters are used when no lists of the sample population are
available.

The problem with random sampling methods when we have to sample a population that's
disbursed across a wide geographic region is that you will have to cover a lot of ground
geographically in order to get to each of the units you sampled. Imagine taking a simple random
sample of all the residents of New York State in order to conduct personal interviews. By the
luck of the draw you will wind up with respondents who come from all over the state. Your
interviewers are going to have a lot of traveling to do. It is for precisely this problem that cluster
or area random sampling was invented.

E) Multistage Area Sampling

Multistage area sampling is sampling that involves using a combination of other probability
sampling techniques. It involves two or more steps. Progressively smaller, lower-population
geographic areas are randomly selected in a series of steps.

The four methods we've covered so far -- simple, stratified, systematic and cluster -- are the
simplest random sampling strategies. In most real applied social research, we would use
sampling methods that are considerably more complex than these simple variations. The most
important principle here is that we can combine the simple methods described earlier in a variety
of useful ways that help us address our sampling needs in the most efficient and effective manner
possible. When we combine sampling methods, we call this multi-stage sampling.

4.2.1.2. Non-probability Sampling

Not all elements have the probability of being selected. The non-probability sampling includes

Compiled Note For Research Method In Economics Page 8

I) Convenience sampling
Convenience sampling: is the sampling procedure used to get those units or people most
conveniently available. For instance, it may be convenient and economical to sample employees
in companies in a nearby area. Researchers are convenience samples to get a large number of
completed questionnaires quickly and economically.

II) Judgment or Purposive or Expert Sampling

Judgment or purposive sampling is a non-probability sampling technique in which an
experienced individual selects the sample based on his judgment. The researcher selects a sample
to serve a specific purpose. Expert sampling, also called judgment sampling, is where the
researcher interviews a panel of individuals known to be expert in a field. Expertise is any
special knowledge, not necessarily formal training. Depending on the topic of study, experts may
be policy issue academics or devotees to a popular culture fad. Critical case sampling is a variant
of expert sampling, in which the sample is a set of cases or individuals identified by experts as
being particularly significant (ex., award winners in a given field).

III) Quota Sampling

It is a non-probability sampling procedure that makes sure that certain characteristics of a
population sample will be represented to the exact extent that the researcher desires.

IV) Internet Sampling

There is a rise in the use of Internet surveys that seek information from respondents interacting
with software on Web Sites. Internet surveys allow researchers to reach a large sample rapidly. A
major disadvantage of Internet surveys is the lack of computer ownership and Internet access
among certain sections of the population. Internet surveys are conducted with volunteer
respondents who visit an organization's Web Site. Thus, selecting all visitors to a Website is
convenience sampling. The non-probability sampling includes the following

V) Availability/ haphazard sampling

Availability sampling is where the researcher selects subjects on the basis of availability. Also
called haphazard sampling, examples include interviewing people who emerge from an event or
location, interviewing a captive audience such as one's students, and mail-in surveys printed in
magazines and newspapers.

VI) Snow ball sampling

Chain referral sampling , also called snowball sampling or network sampling, is where the
researcher starts with a subject who displays qualities of interest (eg., being a private militia

Compiled Note For Research Method In Economics Page 9

member), then obtains referred subjects from the first subject, then additional referred subjects
from the second set, and so on.

4.2.2. Random Sampling Error and Non-Sampling Error

Error is a word with a special meaning in sampling theory. It is not synonymous with „mistake‟.
However, a mistake by an interviewer or a wrong answer to a question would each contribute to
error in a survey, whether a sample survey or a census. Fieldwork problems, interviewer-
induced bias, clerical problems in managing amounts of data, etc. would also contribute to error
in a survey, irrespective of whether a sample is drawn or a census is taken. Biases or errors due
to such reasons or sources are known as non-sampling error. On the other hand, error which is
attributable to sampling, and which therefore is not present in census-gathered information, is
called sampling error.

Sampling error
Sampling error is the difference between the sample result and the result of a census conducted
by identical procedures. Sampling error occurs because of chance variation in the scientific
selection of sampling units. There is always a slight difference between the true population value
and the sample value, hence, a small sampling error. Sampling error is a function of sample size.
Sample size increases, sampling error decreases.

Sampling errors are random variations in the sample estimates around the true population
parameters. Sampling errors can be calculated only for probability or random samples. The
difference between sampling and non-sampling error is that the extent of the former can be
estimated from the sample variation, whereas the latter cannot.


X z
n
The measurement of sampling error is usually called the precision of the sampling plan.
Sampling error is related to confidence intervals. The Y% confidence interval for the

X is the sample mean

Z is the value of standard variation at a given confidence level (to be read from the
table giving the areas under normal curve Z=1.96 for a 95% confidence level,
Z=1.645 for 90% confidence level, Z=2.57 for 99%

n is the sample size

 is the standard deviation of the sample mean Sampling error is given by

z
n
Compiled Note For Research Method In Economics Page 10
Systematic or non-sampling Errors:

It is error resulting from some imperfect aspect of the research design that causes response errors
or from a mistake in the execution of the research. It is also an error that comes from such
sources as sample bias, mistakes in recording responses, and non-responses from persons who
were not contacted or who refused to participate. The non- sampling error includes Non-
coverage error, Wrong population is being sampled, Non-response, Instrument error, Interview
error.

(1) Non coverage error – sampling frame defects: this is where some part of the population are
not included in the sample. Non coverage error also occurs when the list used for sampling are
incomplete or are outdated data. For instance
- Omission of part of the intended population. e.g. soldiers, students living on campus,
people in hospitals, prisoners, etc are typically excluded from national samples.
- These omissions are unlikely to affect national results by more than 1%.

(2) The wrong population is sampled: Researchers must always be sure the group being
sampled is drawn from the population they want to generalize about (intended population).

E.g.1 Drawing a sample of college students to generalize about all college-age persons.

E.g.2 Survey swimmers at the city pool to determine whether the admission price is so high to
discourage use of the pool. Potential users who have already found the price too high will not be
among the swimmers.

(3) The response rate is low (non-response): Some people refuse to be interviewed because they
are ill, are too busy, or simply do not trust the interviewer

(4) Instrument error: The word “instrument” in sampling survey jargon means the device by
which we collect data – usually a questionnaire filled out by the respondent. Different wording of
a question can lead to different answers being given by a respondent. When a question is badly
worded, the resulting error is called instrument error. e.g. leading question or carelessly worded
questions may be misinterpreted by some respondents.
( 5) Interviewer error: This occurs when some characteristic of the interviewer, such as age or
sex, affects the way in which respondent answer questions. e.g. questions about racial
discrimination might be differently answered depending on the racial group of the interviewer.
-----------------------------------------------------------//------------------------------------------------------

Compiled Note For Research Method In Economics Page 11