SAMPLING METHODS & FTC-204

SCALING TECHNIQUE
WHAT IS A SAMPLE?
Sampling is the process of
selecting a few (a sample) from a
bigger group (the sampling
population) to become the basis
for estimating or predicting the
prevalence of an unknown piece
of information, situation or
outcome regarding the bigger
group.

A sample is a subgroup of the

population you are interested in.
WHY DO WE NEED A SAMPLE?
 DIFFERENCES BETWEEN SAMPLING IN
QUANTITATIVE AND QUALITATIVE RESEARCH
In quantitative research you attempt to select a sample in such a way that it is
unbiased and represents the population from where it is selected.

In qualitative research, you make every effort to select either a case that is similar
to the rest of the group or the one which is totally different. A number of factors
may influence the selection of a sample such as:
 the ease in accessing the potential respondents;
 your judgement that the person has extensive knowledge about an episode, an
event or a situation of interest to you;
 how typical the case is of a category of individuals or simply that it is totally
different from the others.
Such considerations are not acceptable in quantitative research.
THE PURPOSE OF SAMPLING
- In Quantitative Research: to draw inferences about the group from which
the sample has been selected.

- In Qualitative Research:
• to either gain in-depth knowledge about a situation/event/episode
• to know as much as possible about different aspects of an individual on the
assumption that the individual is typical of the group and hence will provide
insight into the group.
 FACTORS AFFECTING THE INFERENCES DRAWN
FROM A SAMPLE
Two factors may influence the degree of certainty about the inferences drawn from a
sample:
1. The size of the sample – Findings based upon larger samples have more certainty
than those based on smaller ones.
As a rule, the larger the sample size, the more accurate the findings.
2. The extent of variation in the sampling population – The greater the variation in
the study population with respect to the characteristics under study, for a given sample
size, the greater the uncertainty.
If a population is homogeneous (uniform or similar) with respect to the characteristics
under study, a small sample can provide a reasonably good estimate, but if it is
heterogeneous (dissimilar or diversified), you need to select a larger sample to obtain
the same level of accuracy.
As a rule, the higher the variation with respect to the characteristics under study in the
study population, the greater the uncertainty for a given sample size.
 Types of Sampling

Random/Probability Non-Random/Non- Mixed sampling

sampling probability sampling

Simple random Stratified random Systematic

sampling sampling Cluster sampling sampling
Quota sampling

Single stage
Proportionate
stratified sampling Judgemental
sampling

Double stage
Accidental sampling
Disproportionate
stratified sampling

Multi-stage Snowball sampling

Expert sampling
RANDOM/PROBABILITY SAMPLING DESIGNS
For a design to be called random sampling or probability
sampling, it is imperative that each element in the
population has an equal and independent chance of
selection in the sample.

Equal implies that the probability of

selection of each element in the
population is the same; that is, the choice
of an element in the sample is not
influenced by other considerations such
as personal reference.

The concept of independence means that the choice of one element is not
dependent upon the choice of another element in the sampling; that is, the
selection or rejection of one element does not affect the inclusion or exclusion
of another.
RANDOM/PROBABILITY SAMPLING DESIGNS
A sample can only be considered a random/probability sample (and therefore
representative of the population under study) if both these conditions are met.
Otherwise, bias can be introduced into the study.
There are two main advantages of random/probability samples:
1. As they represent the total sampling population, the inferences drawn from such
samples can be generalised to the total sampling population.
2. Some statistical tests based upon the theory of probability can be applied only
to data collected from random samples. Some of these tests are important for
establishing conclusive correlations.
SIMPLE RANDOM SAMPLING (SRS)
The most commonly used method of selecting a probability
sample.

In line with the definition of randomisation, whereby

each element in the population is given an equal and
independent chance of selection, a simple random
sample is selected by a procedure.

For e.g., there are 80 individuals in a community. The

first step of SRS is to identify each individual by a
number from 1 to 80.
Suppose you decide to select a sample of 20 using the In SRS, Respondents are
simple random sampling technique. selected from a larger group

Using the fishbowl draw, the table for random numbers or a computer program 20
individuals are selected. These 20 individuals become the basis of your enquiry.
METHODS OF DRAWING A RANDOM SAMPLE
Of the methods that you can adopt to select a random sample the three most
common are:
1. The fishbowl draw –
 If your total population is small, an easy procedure is to number each element
using separate slips of paper for each element, put all the slips into a box
and then pick them out one by one without looking, until the number of slips
selected equals the sample size you decided upon.
 This method is used in some lotteries.
2. Computer program –
 there are a number of programs that can help you to select a random sample.
3. A table of randomly generated numbers –
 most books on research methodology and statistics include a table of
randomly generated numbers in their appendices. You can select your sample
using these tables.
STRATIFIED RANDOM SAMPLE
The accuracy of the population estimate largely depends
on the extent of variability or heterogeneity of the study
population with respect to the characteristics that have a
strong correlation with what you are trying to ascertain.

Therefore if the heterogeneity in the population

can be reduced by some means for a given
sample size you can achieve greater accuracy
in the population estimate. Stratified random
sampling is based upon this logic.

In stratified random sampling the researcher attempts to stratify the population in such
a way that the population within a stratum is homogeneous with respect to the
characteristic on the basis of which it is being stratified.

It is important that the characteristics chosen as the basis of stratification are clearly
identifiable in the study population. For example, it is much easier to stratify a
population on the basis of gender than on the basis of age, income or attitude.
 STRATIFIED RANDOM SAMPLING
Once the sampling population has been separated into non-overlapping groups, you
select the required number of elements from each stratum, using the simple random
sampling technique.
There are two types of stratified sampling: proportionate stratified sampling and
disproportionate stratified sampling.
In proportionate stratified sampling, the number of elements from each stratum is taken
in proportion in the total population is selected, whereas in disproportionate stratified
sampling, consideration is not given to the size of the stratum.
CLUSTER SAMPLE
Simple random and stratified sampling techniques are
based on a researcher’s ability to identify each element in
a population.
It is easy to do this if the total sampling population is small,
but if the population is large, as in the case of a city, state
or country, it becomes difficult and expensive to identify
each sampling unit.
In such cases, the use of cluster sampling is more
appropriate.

Cluster sampling is based on the ability of the researcher to divide the sampling
population into groups (based upon visible or easily identifiable characteristics), called
clusters, and then to select elements within each cluster.

Clusters can be formed on the basis of geographical proximity or a common

characteristic that has a correlation with the main variable of the study (as in stratified
sampling).
HOW TO CLUSTER SAMPLE?

The first step would be

defining the
characteristics of the
population and
subsequent sampling.
Population could be
characterized according
to gender, sex,
educational qualification
etc.
 The quality of your clusters and
how well they represent the
larger population determines
the validity of your results.
Ideally, you would like for your
clusters to meet the following
criteria:
•Each cluster’s population should
be as diverse as possible. You
want every potential
characteristic of the entire
population to be represented in
each cluster.

•Each cluster should have a similar distribution of characteristics as the distribution of the
population as a whole.
•Taken together, the clusters should cover the entire population.
•There not be any overlap between clusters (i.e. the same people or units do not appear in
more than one cluster).
HOW TO CLUSTER SAMPLE?
If each cluster is itself a mini-
representation of the larger
population, randomly selecting and
sampling from the clusters allows
imitation of simple random
sampling, which in turn supports the
validity of your results.
Conversely, if the clusters are not
representative, then random
sampling will allow you to gather
data on a diverse array of clusters,
which should still provide you with
an overview of the population as a
whole.

In double- or multi-staged system, these clusters

can be sub-categorized further.
 Record data obtained from clusters.

In multi-stage clustering, rather than collect data

from every single unit in the selected clusters, you
randomly select individual units from within the
cluster to use as your sample.
You can then collect data from each of these
individual units – this is known as double-stage
sampling.
 Types of Sampling

Random/Probability Non-Random/Non- Mixed sampling

sampling probability sampling

Simple random Stratified random Systematic

sampling sampling Cluster sampling sampling
Quota sampling

Single stage
Proportionate
stratified sampling Judgemental
sampling

Double stage
Accidental sampling
Disproportionate
stratified sampling

Multi-stage Snowball sampling

Expert sampling
NON-PROBABILITY SAMPLING
NON-PROBABILITY SAMPLING DESIGNS
Non-probability sampling designs do not follow the theory of probability in the
choice of elements from the sampling population.
Non-probability sampling designs are used when the number of elements in a
population is either unknown or cannot be individually identified.
There are five commonly used non-random designs, each based on a different
consideration, which are commonly used in both qualitative and quantitative
research. These are:
1. Quota sampling;
2. Accidental sampling or Convenience sampling;
3. Judgemental sampling or Purposive sampling;
4. Expert sampling;
5. Snowball sampling.
QUOTA SAMPLING
The main consideration directing quota sampling is the researcher’s ease of access to
the sample population.
The researcher selects the sample according to a visible characteristic, such as gender
or race, of the study population that is of interest to you.
The sample is selected from a location convenient to the researcher, and whenever a
person with this visible relevant characteristic is seen that person is asked to
participate in the study.
The process continues until the researcher contacts the required number of respondents
(quota).
QUOTA SAMPLING
The advantages of using this design are:
 It is the least expensive way of selecting a sample;
 The researcher does not need any information, such as a sampling frame, the
total number of elements, their location, or other information about the sampling
population;
 It guarantees the inclusion of the type of people needed
The disadvantages are:
 As the resulting sample is not a probability one, the findings cannot be
generalised to the total sampling population.
 Also, the most accessible individuals might have characteristics that are unique to
them and hence might not be truly representative of the total sampling
population.
ACCIDENTAL OR CONVENIENCE SAMPLING
Researcher
Accidental sampling is based upon
convenience in accessing the sampling
population.
While quota sampling attempts to
include people possessing an
obvious/visible characteristic,
accidental sampling makes no such
attempt. You stop collecting data when
you reach the required number of
respondents you decided to have in
your sample.
This method of sampling is common
among market research and
newspaper reporters.
 ACCIDENTAL OR CONVENIENCE SAMPLING
Accidental sampling is based upon convenience in accessing the sampling population.
While quota sampling attempts to include people possessing an obvious/visible
characteristic, accidental sampling makes no such attempt. You stop collecting data
when you reach the required number of respondents you decided to have in your
sample.
This method of sampling is common among market research and newspaper reporters.

It has more or less the same

advantages and
disadvantages as quota
sampling but as the
researcher is not guided by
any obvious characteristics,
some people contacted may
not have the required
information.
JUDGEMENTAL OR PURPOSIVE SAMPLING
The primary consideration in purposive sampling is researcher’s judgement of
who can provide the best information to achieve the objectives of your study.
The researcher only approaches those people who in their opinion are likely
to have the required information and be willing to share it with you.
This type of sampling is extremely useful when you want to construct a
historical reality, describe a phenomenon or develop something about which
only a little is known.
This sampling strategy is more common in qualitative research, but in
quantitative research you select a predetermined number of people who, in
your judgement, are best positioned to provide you the needed information
for your study.
JUDGEMENTAL OR PURPOSIVE SAMPLING
SNOWBALL SAMPLING
Snowball sampling is the process of selecting a sample using networks. To
start with, a few individuals in a group or organisation are selected and the
required information is collected from them.
They are then asked to identify other people in the group or organisation,
and the people selected by them become a part of the sample.
Information is collected from them, and then these people are asked to
identify other members of the group and, in turn, those identified become the
basis of further data collection.
This process is continued until the required number or a saturation point has
been reached, in terms of the information being sought.
SNOWBALL SAMPLING
 EXPERT
SAMPLING
The only difference between judgemental sampling and expert sampling is that in
the case of the former it is entirely your judgement as to the ability of the
respondents to contribute to the study.
But in the case of expert sampling, your respondents must be known experts in the
field of interest to you.
The number of people you talk to is dependent upon the data saturation point
whereas in quantitative research you decide on the number of experts to be
contacted without considering the saturation point.
You first identify persons with demonstrated or known expertise in an area of
interest to you, seek their consent for participation, and then collect the
information either individually or collectively in the form of a group.
 Types of Sampling

Random/Probability Mixed
Non-Random/Non- sampling
sampling probability sampling

Simple random Stratified random Cluster Systematic

sampling sampling sampling Quota sampling
sampling

Single stage
Proportionate
stratified sampling Judgemental
sampling

Double stage Accidental

Disproportionate sampling
stratified sampling

Snowball
Multi-stage sampling

Expert
sampling
MIXED SAMPLING DESIGN
Systematic sampling has been classified as a ‘mixed’ sampling design
because it has the characteristics of both random and non-random sampling
designs.
In systematic sampling the sampling frame is first divided into a number of
segments called intervals.
Then, from the first interval, using the SRS technique, one element is selected.
The selection of subsequent elements from other intervals is dependent upon
the order of the element selected in the first interval.
For e.g., If in the first interval it is the fifth element, the fifth element of each
subsequent interval will be chosen.
MIXED SAMPLING DESIGN
Non-probability sampling designs do not follow the theory of
probability in the choice of elements
from the sampling pop
TO SUMMARIZE:
TO SUMMARIZE: