Sampling Techniques

Type of sampling techniques:

a) Probability Sampling/Random Sampling
b) Non-Probability Sampling/Non-random
sampling
Probability Sampling
• A sampling technique where each and every element of the
population has an independent chance of being selected as the
sample unit.
• Personal prejudice and biases do not work.
Types:-
1. Simple random sampling
2. Stratified random sampling
3. Systematic random sampling
4. Cluster sampling
5. Multistage Sampling
Simple Random Sampling
• is a method of sampling in which each member of the population have an equal
probability of selection as a sample. It is free from sampling bias.

• To conduct a simple random sample, the researcher must first prepare an

exhaustive list (sampling frame) of all members of the population of interest. From
this list, the sample is drawn so that each person or item has an equal chance of
becoming drawn during each selection round.
• Therefore, simple random sampling is a method of selecting ‘n’ units out of
population size ‘N’ units by giving the equal probability to all units.

• For example, a researcher is interested study about students’ behaviors at college

where there are 1000 students. Researcher has to select 100 students for his study. For
that, researcher can select samples by writing every student’s symbol number on a
piece of paper and put in a hat. Selecting the sample from the hat is random and each
student has an equal chance of being selected.
Samples may be drawn with or without replacement.
• Simple random sampling with replacement:
If the sample element is selected once and may be selected again in the
next drawing, this sampling procedure is called simple random sampling
without replacemnet. Each element is returned to the sampling frame
after it is selected so that it may be sampled again.
• Simple random sampling without replacement:
If the sample element is selected once and cannot be selected again, this
sampling procedure is called simple random sampling without sampling.
Each element selected for the sample is then excluded from the
sampling frame.
Some of the procedures for selecting random sampling are as follow:
Lottery method:
In lottery method, the populations are numbered on small and
identical slips of paper which are folded and mixed together in a drum
or in a flat container. A blindfold selection is then made from the
number of slips required to constitute the desired size of sample.
Use of random number tables: Under this method random number
table which has been so constructed that each of the digits from 0, 1, 2
... 9 appears with approximately the same frequency and
independently with each other. The best way to choose a sample is to
use a random number table (or let a computer generate a series of
random numbers automatically).
Steps in selecting a simple random sample:
• Define the target population
• Identify an existing sampling frame of the target population or
develop a new one
• Evaluate the sampling frame for under-coverage, over-coverage,
multiple coverage, and clustering, and make adjustments when
necessary
• Assign a unique number to each element in the frame
• Determine the sample size
• Randomly select the targeted number of population elements.
Advantages
• One of the greatest advantages of the simple random sampling
method is that it needs only a minimum knowledge of the study
group of population in advance.
• It is free from errors in classification/stratification.
• It is totally free from bias and prejudice.
• The method is simple to use.
• It is very easy to assess the sampling error in this method.
Disadvantages
• As compared to stratified sampling, it gives less efficient results for
the same sample size.
• The study of the sample becomes time-consuming if the units or
items are widely dispersed.
• It cannot be employed if the units of the population are
heterogeneous in nature.
• This method does not use available knowledge about the population.
• It needs a complete list of units in the population (sampling frame).
• It does not always produce a representative sample.
Systematic Sampling
• It is a method of sampling in which sample elements are selected from a list
or from sequential files based on a system of intervals in a numbered
population. In this method, the first element is selected randomly from a list
or from sequential files, and then every nth element is selected.
• Steps in systematic sampling
➢Number the units in population from 1 to N
➢Decide on the n (sample size) that is required
➢Select an interval size k=N/n
➢Randomly select an integer between 1 to k
➢Finally, take every kth unit
For example, a researcher is interested to study about students’
behaviors at a college where there are 1000 students. Researcher has
to select 100 students for his study. For that, students would be put
into list form and then every 10th student would be selected for
inclusion in the sample.
Advantages
• Systematic sampling is less costly and easier to implement than SRS.
It is because in this method random selection is done only for the
first unit.
• It ensures representativeness across the list (population) and is easy
to implement.
• It can help eliminate cluster selection i.e. selection of nearby units
of the population.
Disadvantages
• It works well only if the complete and up-to-date frame is available
and if the units are randomly arranged in the frame; for this reason,
the units are arranged in some order say alphabetically or in
increasing/decreasing order of value before selecting a sample.
• If the population has a periodicity of the trait, this sampling
technique may not give a representativeness sample. So, it should
not be used if the population already has some pattern.
Stratified sampling:
• This method is used when samples are needed from heterogeneous
population.
• Stratified random sampling is defined as a combination of
independent samples selected in proper proportions from
homogeneous groups within a heterogeneous population.
• Stratified sampling is a method of probability sampling in which the
target population is first categorized into mutually exclusive,
homogeneous segments (strata), and then a simple random sample is
selected from each segment (stratum).
• The samples selected from the various strata are then combined into
a single sample.
Allocation of Sample size in Stratified sampling
Proportional Allocation:
• In this type of allocation, the sample size to be selected from the various
strata is given by: ni= (n/N)*Ni; where ni is the size of the sample from the
ith strata, Ni is the population size of the ith strata; n is the total sample size
and N is the population size.
Optimum allocation:
ni’s are chosen so as to
• Maximize the precision for fixed sample size n; Neyman’s Allocation
• Maximize the precision for a fixed cost or
• Minimize the total cost for fixed desired precision; For each of these three
allocations, specific mathematical formulae are available.
Disproportionate Allocation:
• No. of items selected from a stratum is independent of stratum size.
Proportional Allocation:
• The number of Vouchers coming from 3 treasuries are 300, 200, and
500 respectively. Find out the size of the sample to be selected from
each treasury if a proportional stratified sample of size 60 is required.
• Here N1 = 300, N2 = 200 and N3 = 500; N = 1000
• using ni = (n/N)*Ni; i = 1, 2, 3
• n1 = (60/1000)* 300 = 18, n2 = (60/1000)* 200 = 12 and n3 =
(60/1000)* 500 = 30.
• Thus, a sample of 18, 12, and 30 vouchers will be selected from these
strata. Actually, the principle followed here is that the larger the size
of the Strata, the larger should be the sample from that Strata.
Steps in stratified sampling
• Determine the variables to use for stratification.
• Determine the proportionate stratification based on study’s
information needs and risks.
• Divide the sampling frame into separate frames for each stratum.
• Randomize the elements within each stratum’s sampling frame.
• Follow random or systematic procedure to draw the sample.
Example 1, a researcher is interested to study about students’ behaviors
at college where there are 1000 students. Researcher has to select 100
students for his study. For that, students of that college is separated or
categorized into first, third, fifth, and seventh semesters. There are
four strata of students population (first, third, fifth, seventh semesters)
from which researcher can select his sample using simple random
sampling technique of 25 samples from each semester.
Example 2

Example of stratified sampling

Population All people in Nepal
Groups (strata) 7 newly constructed Provinces in Nepal
(Province 1, Madesh, Bagmati, Gandaki,
Lumbini, Karnali and Sudurpaschhim)
Simple random sampling 500 people from each Provinces.
Sample Size 7x500=3500 selected people
Advantages
1. Stratified sampling is more precise if the variable of interest is associated
with strata.
2. In this kind of sampling all the subgroups are represented, allowing
separate conclusions about each of them; say separate conclusions for each
state/District/treasury.
3. The stratified random sample also improves the representation of the
various groups within the population, as well as ensures that strata are not
over/under-represented. It helps the researcher/auditor to compare strata,
as well as make more valid inferences about the population from the
sample.
Disadvantages
1. In this method, sampling error is difficult to measure.
2. There is a loss of precision if a small number of units are sampled in
individual heterogeneous strata.
3. This method is useful when there is sufficient knowledge about the
spread/variability of the population so that the strata are homogeneous.
Cluster Sampling:
• It is a method of sampling in which elements of the population are
randomly selected in naturally occurring grouping (clusters).
• It is similar to stratified sampling because the population to be
sampled is subdivided into mutually exclusive groups. However,
these groups are referred to as clusters instead of strata because
they are “naturally occurring groupings such as schools, households,
or geographic units.”
• In stratified random sampling, all the strata of the population is
sampled while in cluster sampling, the researcher only randomly
selects a number of clusters from the collection of clusters of the
entire population. Therefore, only a number of clusters are
sampled, all the other clusters are left unrepresented.
Steps in cluster sampling
• Divide the population into clusters
• Randomly sample clusters
• Measure all units within sampled clusters
Example, a researcher is interested to study about students’ behaviors at
college where there are 1000 students. Researcher has to select 100
students for his study. For that, students of that college is separated or
categorized into first, third, fifth, and seventh semesters which
constitute sampling frame. But the numbers of students are too large.
Researcher might then restrict himself with first and third semester,
which constitute the secondary sampling frame. Finally researcher
would select students from each of these semesters. Researcher then
selects these students for samples.
Example of cluster sampling
Population All people in Nepal
Groups 7 newly constructed Provinces in Nepal
(Clusters) (Province 1, Madesh, Bagmati, Gandaki,
Lumbini, Karnali and Sudurpaschhim)
Simple random 2 Provinces from 7 Provinces.
sampling
Sample Every people in the 2 selected Provinces.
Multi-stage Sampling:
• Multi-stage sampling represents complex form of cluster
sampling in which population is divided into groups (clusters) and
then, one or more clusters are selected at random and everyone
within the chosen cluster is sampled.
• This is a further development of the idea of cluster sampling. This
technique is meant for big inquiries extending to a considerably
large geographical area like an entire country.
• Under multi-stage sampling the first stage may be to select large
primary sampling units such as states, then districts, then towns
and finally certain families within towns. If the technique of
random-sampling is applied at all stages, the sampling procedure
is described as multi-stage random sampling.
Advantages
1. It is simple as a complete list of units (sampling frame) is
required only for the clusters selected in the sample which
reduces efforts of finding out the complete sampling frame for
all the clusters.
2. For this kind of sampling less travel/resources are required.
Disadvantages
1. It is imprecise if clusters are homogeneous (A large sample
as compared to SRS is required for the same precision)
2. In this kind of sampling; Sampling Error is difficult to
measure.
The steps in multi-stage sampling are as follows:
• Organize the sampling process into stages where the unit of
analysis is systematically grouped.
• Select a sampling technique for each stage.
• Systematically apply the sampling technique to each stage
until the unit of analysis has been selected.
Example
Non-probability sampling
• A sampling where each element of the population has not an equal chance of
being selected as a sample and sampling is based on a pre-plan is known as
non-probability sampling.
• Such sampling is considered appropriate if the researcher needs to collect
data with low cost and time and generalization of findings is not essential.
• There is a chance of biases in selecting a sample by using this method.
Types:-
1.Purposive or judgmental sampling
2.Quota sampling
3.Convenience sampling
4.Snowball sampling
Non-probability sampling tends to:
• These are cheaper
• These are used when a sampling frame is not available
• These are useful when the population is so widely
dispersed that cluster sampling would not be efficient
Convenience/Accidental/Haphazard sampling
• It is a sampling method in which samples are selected based on
researcher’s ease or comfort of access.
• The samples are selected in accordance to the
requirement/convenience of the researcher.
• It is not normally representative of the target population because
sample units are only selected if they can be accessed easily and
conveniently.
• It is the least costly, in terms of time, effort and money, but may
result in poor quality data and lacks intellectual credibility.
Example, a researcher is interested study about students’ behavior in
college where there are 1000 students. If the researcher is only
interested in achieving a sample size of say 100 students, he may simply
stand at one of the main entrance to college, where it would be easy to
invite and interview those students to take part in the research.
Likewise other examples could be:
• The female moviegoers sitting in the first row of a movie theater
• The first 100 customers to enter a department store
• The first three callers in a radio contest.
Merits
• Quick method of data selection
• It can be used when the population is not clearly defined
Demerits
• Sample may not represent the population as a whole
• It may be biased
Quota Sampling:
• It is a sampling method in which sample is based on the judgment of
the researcher.
• It is judgmental sampling technique in which the first stage consists of
developing categories or quotas of the population and the second
stage consists of sample elements being selected in convenience or
judgment.
In quota sampling:
• Firstly, a population is segmented into mutually exclusive sub-groups,
just as in stratified sampling.
• Secondly, judgment is used to select the subjects or units from each
segments based on specified proportion.
Steps in quota sampling
• Divide the population into strata, or groups of individuals that are
similar (or homogeneous) in some way that is important to the
response.
• Choose a separate sample from each spectrum. This does not have to
be random sample.
• Combine these samples to form a quota sample.
• Example, a researcher is interested study about students’ behavior in
college where there are 1000 students. Since he believes male and
female students have different behaviors, the researcher decides to
stratify the population by gender.
• In the first step: from student attendance sheets, he knows that 60% of
students are female. He wants a sample of size 200. To get a
proportional sample, he decides to sample 120 females and 80 male
students.
• In the second step: researcher might be tempted to interview those
120 females and 80 male students.
Merits
• It is a cheap method
• It is an effective method
Demerits
• It may be biased
• It may not be representative of the population
Judgment/Purposive sampling:
• It is a sampling method in which sample are selected based on
researcher’s judgment or interest or knowledge that s/he believed
those selected sample addresses the purpose of a particular research
problem under investigation.
• In other words, the researcher chooses the sample based on who
they think would be appropriate for the study.
• The researcher uses his/her own judgment about which respondents
to choose, and picks those who best meets the purpose of the study.
Thus, the sample representatives are highly dependent upon the
good judgment of the researcher.
• The judgment sampling is appropriate when the desired population
for the study is uncommon or very difficult to locate and employ.
The researcher targets a particular group of people whose
background expertise relates to the objective of the study.
• Example, if a researcher want to study an impact of undeclared
economic sanction in Nepal by India, researcher select a sample of
twenty of the senior Nepalese professor to provide their opinion on
the subject. Researcher considers that the judgments of these
professors are much more superior to the sample rather than the
opinion of researcher’s neighbors.
Merits
• Simple method of sampling
• Practical method for quick decision for urgent need
• Better for small sample size
Demerits
• May not be representative of the population
Snowball Sampling:
• It is a sampling method in which samples are selected based on
referrals- using existing interview subjects as a means of making
contact with others.
• This sampling method is used where the respondents for the study
are difficult to identify and best located through referral networks.
• For sampling, an initial group of individuals are discovered, and then
subsequent respondent, possessing similar characteristics, are
identified based on referrals provided by the initial respondents.
• Researcher starts with one or two information rich respondents and
ask them if they know persons who know a lot about researcher’s
topic of interest or who represent the characteristics researcher are
interested in.
• The snowball sampling method is appropriate to study drug culture,
individuals with HIV/AIDS, prostitutes, teenage gang activities, black
markets, political environments, power elites etc. where respondents
are difficult to identify and contact.
Steps in snowball sampling
• Try to identify one or more units in the desired population
• Use these units to find further units and so on until the sample size is
met
Merits
• It is a cheap method
• It is an effective method
• It can be used in hidden population
Demerits
• It is a time-consuming method
• Lack of representativeness