Unit 5

Sample and Sampling

Procedures
 ……Cont.
The key steps in sampling design involve
defining the target population, selecting a
sampling method, determining the sample
size, and implementing the sampling plan.
Below is a step-by-step guide to the sampling
design process:
1. Define the Research Objectives
Start by clarifying the purpose of the research and
the key questions to be answered.
This helps determine the type of data needed and the
appropriate sampling strategy.
 ……Cont.
2. Define the Target Population
The target population is the group from which
you will draw the sample.
It should be clearly defined to ensure that the
results are generalizable.
3. Select the Sampling Frame
A sampling frame is a list or database that
includes all members of the target
population.
It serves as the source from which the
sample will be drawn.
 ……Cont.
4. Choose a Sampling Method
Select a method based on the research
goals, population characteristics, and
available resources.
Sampling Methods:
Method Description When to Use
Every member of the When you need a
Probability Sampling population has a known, non- representative sample for
zero chance of selection. generalization.

When time or resources are

Not every member has a known
Non-Probability Sampling limited, or for exploratory
chance of selection.
research.
 ……Cont.
Types of Probability Sampling:
Simple Random Sampling
Stratified Sampling
Cluster Sampling
Systematic Sampling
Types of Non-Probability Sampling:
Convenience Sampling
Judgmental Sampling
Quota Sampling
Snowball Sampling
 ……Cont.
5. Determine the Sample Size
Calculate the sample size needed to ensure
accurate and reliable results. The size
depends on:
Population size
Margin of error (e.g., ±5%)
Confidence level (e.g., 95%)
Variance or variability in the population
 ……Cont.
6. Implement the Sampling Plan
Once the sampling method and size are
determined, draw the sample from the sampling
frame.
Steps:
• Randomize the selection (for probability
sampling).
• Use appropriate tools or software for systematic
selection.
• Ensure the sample matches the characteristics of
the population.
 ……Cont.
7. Collect the Data
Administer surveys, interviews, or other data

collection methods to the sample group.

8. Assess the Sampling Process and Address Bias

Evaluate the sampling process to identify and

mitigate potential biases.

 Summary of Key Steps

Step Description

1. Define Research Objectives Identify the purpose of the study.

2. Define the Target Population Specify who or what is being studied.

Identify the source from which the sample is

3. Select the Sampling Frame
drawn.

Select a probability or non-probability

4. Choose a Sampling Method
technique.

5. Determine Sample Size Calculate the number of participants required.

6. Implement the Sampling Plan Draw the sample using the chosen method.

7. Collect the Data Conduct surveys, interviews, or observations.

8. Assess the Process Review and address potential biases.

 4.4. Sample and Sampling Procedures
4.1. Population :-
Population is the entire mass of observations
from which a sample is to be formed.
It is the universe from which sample is drawn.

 Population represents the whole mass of the

interest to the researcher՚s.
A survey conducted based on the basis of all
 ……Cont.
Population/Census vs. Sample:
When only some elements are selected from a
population, we refer to that as a sample; when all
elements are included, we call it a census.
A Census is a systematic process of collecting,
recording, and analyzing data about every member of a
population, in which every individual in the population,
providing a complete and detailed dataset
A sample is “a smaller (but hopefully representative)
collection of units from a population used to determine
 ……Cont.
4.2. The Need for Sampling (Why sampling?)
1) Cost and Resource Efficiency:
 Collecting data from an entire population can be expensive
and time-consuming.
 Sampling allows researchers to gather information from a
smaller subset of the population,
 By doing this, a researcher can reduce costs and resource
requirements.
 It is often more practical and feasible to collect data from a
sample, especially when the population size is large or
geographically dispersed.
 ……Cont.

2) Time Constraints:
Conducting research with a sample allows for quicker
data collection and analysis compared to studying the
entire population.
It saves time by focusing efforts on a smaller group,
enabling researchers to obtain results more efficiently.
This is particularly beneficial in time-sensitive
research projects or situations that necessitate prompt
decision-making.
 ……Cont.
3) Manageable Data Collection:
 Working a research with a sample makes data collection
more manageable.
 Researchers can concentrate their efforts on a smaller
group, allowing for more detailed and thorough data
collection methods.
 Furthermore, it is more convenient and reliable to store and
conduct statistical analyses on smaller datasets.
 This also facilitates in-depth insights and a more
comprehensive understanding of the research topic.
 ……Cont.
4) Ethical Considerations:
In certain cases, collecting data from an entire
population may pose ethical challenges, such as
invasion of privacy or burdening participants.
Sampling helps protect the privacy and well-being
of individuals by reducing the burden of data
collection.
It allows researchers to obtain valuable information
 ……Cont.
4.3. Determine the Sampling Frame
Sampling frame is a list of population elements (people,
companies, houses, cities, etc.) from which units to be
sampled can be selected.
The sampling frame (list of the target population) is the
list from which the potential respondents are drawn.
Sampling frame error occurs when certain elements of
the population are accidentally omitted or not included
on the list.
 ………Cont.
A sample (n) is a subset of a population (N) to which
the researcher has selected with a due care and intends
to generalize the results of the study to the entire
population.
 Sampling frame: -A list of every individual in the
population
• Frame is either constructed by the researcher or
some existing list of population is used.

 Sampling- is the process of selecting sample from

population :-
• It is the the procedure employed to draw sample.
 ….Cont.
 A sample unit
 A sample unit is the basic entity or element that is selected
for data collection in a study.
 It is a single member or item of the population that
provides information for analysis.
 Key Characteristics of a Sample Unit:
 Individual Element:
• A sample unit represents a single, distinct entity of the population
(e.g., one person, household, organization, or object).
 Relevance:
• It must be relevant to the research objectives and align with the
study's defined population.
 Distinct Identity:
• Sample units are mutually exclusive, meaning no overlap occurs
between units to avoid duplicating data.
….Cont.

19
 ….Cont.
 Important characteristics of sample :-
Goal-oriented: relate to the research objectives
Representing the universe, sample must be adequate.
The sample size should be sufficiently large.
A sample should be selected at random.
A sample should be economical, should be achieved
with minimum cost and effort.
Generalizable with a reasonable level of confidence
 ……Cont.
4.5.Advantages of Sampling
Sampling reduces cost

Sampling gives grater accuracy

Sampling brings speed

Sampling increases scope

Sampling reduces work

We can observe in detail

Easy to manage
Limitations of Sampling :-
 If the sample is not true representative of
population, then false inferences may occur
 We cannot select a sample which can
represent the entire mass.
 That is, a sample always possesses
some error.
 Biased samples may lead to false
generalizations.
 Very less population also give trouble in
sampling.
 4.4. Two Types of Sampling
4.4.1. Probability Sampling
 A probability sampling scheme is one in which
every unit in the population has a chance (greater
than zero) of being selected in the sample, and this
probability can be accurately determined.
 When every element in the population does have
the same probability of selection, this is known as
an 'equal probability of selection' (EPS) design.
 …..Cont.

the sample is selected randomly from a list that

contains all members of the population and used
in quantitative/mixed research.
this technique ensures that the sample is
representative of the population, which allows
researchers to generalize their findings with a
higher degree of confidence.
 ….Cont.
 Types of Probability Sampling:
1. Simple random sampling
 Applicable when population is small, homogeneous and readily

available.
 Because all subsets of the frame are given an equal probability,

each element of the frame has an equal probability of selection

(EPS).
 Hence, simple random sampling is always an equal probability of

selection design.
 A table of random number or lottery system can be used to
 ……Cont.
2. Systematic Sampling
In this technique, the sampling frame is ordered
according to some criteria and elements are selected at
regular intervals through that ordered list.
Systematic sampling involves a random start and then
proceeds with the selection of every k th element from
that point onwards, where k = N/n, where k is the ratio
of sampling frame size N and the desired sample size n,
and is formally called the sampling ratio.
 ……Cont.
3. Stratified Sampling
 Stratified sampling is one obtained by dividing the population
elements into mutually exclusive, non-overlapping groups of
sample units called strata, then selecting a simple random
sample from within each stratum (stratum is singular for
strata).
 Where population embraces a number of distinct categories,
the frame can be organized into separate "strata."
 Each stratum is then sampled as an independent sub-
population, out of which individual elements can be randomly
 ……Cont.
 Every unit in a stratum has same chance of being selected.

 Adequate representation of minority subgroups of interest

can be ensured by stratification & varying sampling fraction
between strata as required.
 Stratifying involves classifying sampling units of the
population into relatively homogeneous groups before
(usually) selecting sample units, such as position, rank,
income, education, sex, religion, or ethnic background.
 The same population can be stratified multiple times
simultaneously.
 ……Cont.

4. Cluster sampling
 If you have a population dispersed over a wide geographic
region, it may not be feasible to conduct a simple random
sampling of the entire population.
 In such case, it may be reasonable to divide the population into
“clusters” (usually along geographic boundaries), randomly
sample a few clusters, and measure all units within that cluster.
 Cluster sampling is an example of 'two-stage sampling'.
 First stage a sample of areas is chosen;
 Second stage a sample of respondents within those areas is
selected.
 ……Cont.
5. Multi-stage sampling
 Multi-stage sampling is a sampling method that divides the
population into groups (or cluster) for conducting research.
 Multi-stage sampling is a complex form of cluster
sampling, sometimes, also known as multistage cluster
sampling.
 The researcher divides the population into groups at various
stages for better data collection, management, and
implementation.
 These groups are called clusters.
 ……Cont.
B) Non-probability Sampling
Non-probability sampling is a sampling
technique where some elements of the
population have no chance of selection.
Non-probability sampling involves the selection
of elements based on assumptions regarding the
population of interest, which forms the criteria
for selection.
 ………Cont.
 Types of Non-Probability Sampling
1. Convenience Sampling
 Sometimes known as opportunity sampling or
haphazard sampling.
 Convenience sampling is used because it is quick,
inexpensive, and convenient.
 Convenience samples are useful for certain purposes, and
they require very little planning.
 Researchers simply use participants who are available at
the moment.
 ………Cont.

The researcher using such a sample cannot

scientifically make generalizations about the total

population from this sample because it would not

be representative enough.

Non-probability sampling is most useful for pilot

testing
 ………Cont.
2. Snowball/Chain-referral Sampling
 In snowball sampling, we start by identifying a few
respondents that match the criteria for inclusion in our study
and then ask them to recommend others they know who also
meet our selection criteria.
 It is done with the help of study subjects to choose other
potential subjects.
 A useful tool for building networks and increasing the number
of participants.
 Depends greatly on the initial contacts and the connections
 ………Cont.

3. Purposive/Judgmental Sampling
The researcher chooses the sample based on who they
think would be appropriate for the study.
This is used primarily when there is a limited number of
people that have expertise in the area being researched.
Used when you want to access a particular subject of
people based on purpose. Start with a purpose in mind.
When taking the sample, the research should reject
people who do not fit a particular profile.
 ………Cont.

4. Quota Sampling
In many large-scale applications of sampling

procedures, it is not always possible or desirable to list

all members of the population and randomly select

elements from that list.

The reasons for using any alternative procedures include

cost, timeliness, and convenience.

 ………Cont.

In quota sampling, the population is first segmented into

mutually exclusive sub-groups, just as in stratified
sampling, and then a non-random set of observations is
chosen from each subgroup to meet a predefined quota.
There is freedom to choose any respondent as long as
the quota is met.
Subjects are recruited as they arrive and the researcher
will assign them to demographic groups based on
variables like age, gender or educational background.
 ………Cont.

4) Determine the Sample Size

 Sample size determination is choosing the correct number of
observations or people from a large group to use in a sample.
 The goal of figuring out the sample size is to ensure that the
sample is big enough to give statistically valid results and
accurate estimates of population parameters but small enough
to be manageable and cost-effective.
 The sample size is an important feature of any study in which
the aim is to make inferences about the population from a
sample.
 ………Cont.
Choosing the statistically significant sample size
depends on a number of things, such as the size of the
population, how precise you want your estimates to be,
how confident you want to be in the results, and how
much money and time you have for the study.
There are many approaches to determine the sample size
among which the followings are the major:-
a) a census for small populations,
b) published tables,
c) applying formulas to calculate a sample size, and
d) imitating a sample size of similar studies .
 ………Cont.

a) Using a Census for Small Populations

One of the approaches to determine sample size is to
use the entire population as the sample.
Although cost considerations make this impossible
for large populations, a census is more attractive for
small populations, for instance for 200 or less
population.
A census eliminates sampling error and provides data
on all the individuals in the population.
 ………Cont.
b) Using Published Tables
 A second way to determine sample size is to rely on published tables,
which provide the sample size for a given set of criteria.
 Krejcie and Morgan (1970) came up with a table for determining
sample size for a given population for easy reference.
 Determining a sample size using a published table involves
referencing a pre-calculated table, often based on common statistical
methods for sampling.
 These tables are typically designed to provide the required sample
size for a population given certain parameters.
 In the following slide, major a step-by-step guide to determine the
sample size are discussed briefly.
 …….Cont.
1. Identify the Population Size
 Determine the size of the total population (N) you are studying.
 If the population size is unknown or infinite, some tables are designed to work with
infinite populations.

2. Decide the Confidence Level

 Most tables are based on confidence levels, commonly 90%, 95%, or 99%.
 A 95% confidence level is most commonly used, meaning you're 95% confident the
results represent the population.

3. Set the Margin of Error (Precision)

 Determine how precise you want your results to be, expressed as a percentage (e.g.,
±5%).
 The margin of error determines how close your sample statistic is expected to be to
 …….Cont.
4. Select the Variability (P)
 If you are unsure about variability in the population, use the
conservative estimate of 50% (P = 0.5), as it requires the largest
sample size.
 If previous data suggests a specific proportion, you can use that
instead.
5. Use the Table
 Locate the table you are using (e.g., Krejcie and Morgan,
Yamane’s formula-based tables, or others).
 Cross-reference your population size with your desired
confidence level and margin of error.
 The table will directly give you the required sample size.
6. Adjust for Response Rate
 If you expect non-responses or incomplete data, increase the
sample size accordingly to ensure sufficient responses.
 ………Cont.

c) Using Formulas to Calculate a Sample Size

 The third approach to determine sample size, is the
application of one of several formulas.
 There are many formulas used for calculating
sample size.
 For example, Taro Yamane (1967) provides a
simplified formula to calculate sample sizes.
 A 95% confidence level and e = .05 are assumed
for the Equation.
 Where n is the sample size, N is the population
size, and e is the level of precision
 …….Cont.
 Taro Yamane's formula: -
n = N/ (1+N (e) 2.
– Where:
– n = sample size
– N = population size
– e = margin of error (expressed as a decimal, e.g., 5% =
0.05)
Example:
– Population size (N) = 10,000
– Margin of error (e) = 5% = 0.05
– n= 10,000/(1+10000/0.05)2 = 384.6
 So, you need a sample size of 385.
 ………Cont.

d) Using a Sample Size of a Similar Study

 The fourth approach is to use the same
sample size as those of studies similar to the
plan.
 Without reviewing the methods used in
these studies may run the risk of repeating
errors that were made in determining the
sample size for another study.