Course – Descriptive Statistical Analysis

Module 1:
Population and Sampling

Learning Objectives
 To understand the concept of population and sample with an example.
 To understand various sampling techniques.

Introduction
Descriptive Statistics involves summarizing and describing the data features through various
measures such as central tendency, dispersion, and shape to have a broad overview of the data
and identify its key patterns and relationships. It can be used to communicate insights about
the data in a concise and meaningful way.

Before knowing various descriptive statistic measures, it is crucial to know the concepts of
population and sample. These concepts provide the framework for researchers to draw
conclusions about larger groups based on smaller subsets of data.

Population and Sample

Population refers to the entire collection of data to be described or analyzed.

A sample is a subset of the population that is selected for observation and analysis. It is chosen
in such a way that it reflects the characteristics of the larger population.
 Figure 1: Population and Sample

Consider a scenario where a pharmaceutical company wants to assess the effectiveness of a

new drug on a specific demographic group, say, adults aged 65 and older. The population, in
this case, would be all adults within this age group. However, it would be impractical and costly
to include every single adult in the study. Instead, the researchers would select a sample of
individuals from this population, randomly choosing 500 participants. By studying this sample,
the researchers can make inferences about the effectiveness of the drug for the entire
population of older adults.

Sampling Techniques
Sampling techniques have a vital role in gathering data effectively for a sample. These
techniques are essential to draw reliable predictions about the characteristics of the entire
population based on the observed sample.

Two types sampling techniques are as follows: -

 Figure 2: Types of Sampling Techniques

In Random Sampling, every unit of the population has an equal probability of being chosen.
This ensures that each time an unbiased sample is chosen. The Random Sampling techniques
can be categorized as below:

Table 1: Random Sampling Techniques

# Sampling Definition When to use Example
Technique
1 Simple Random In this technique, Used for Consider a scenario
Sampling each unit of the populations of any where a survey on
 population has an size (small or customer satisfaction
equal probability of large) is to be conducted. To
being chosen for perform Simple
the sample. This can Random Sampling,
be implemented each reviewer will be
through a random assigned a number,
generator which and then through a
yields random random generator, a
numbers to select certain number of
the sample. reviewers will be
selected as a sample.
This ensures that every
reviewer has an equal
probability of being
selected.
2 Stratified Random In this technique, Used when the Consider a scenario
Sampling the population is population can be where a survey on job
divided into divided into satisfaction is to be
homogenous distinct subgroups conducted. To perform
subgroups referred or strata Stratified Random
to as strata, and Sampling, employees
then samples are will be divided into
selected from each various strata based
stratum. This aims on departments, and
to reduce sampling then a certain number
error by ensuring of employees will be
representation from selected from each
various subgroups. stratum (department)
as a sample.
3 Systematic In this technique, Used for Consider a scenario
Sampling every kth unit of the populations of any where a survey needs
population is size, but to be conducted from
randomly selected particularly a group of 1000
based on the suitable for large workers. To perform
sampling cycle. The populations with a Systematic Sampling
sampling cycle can consistent and select a sample of
be determined from structure. 100 workers, first
the given formula. worker is chosen at
random and then
N every kth worker is
k¿
n selected until a sample
of 100 workers is
n = sample size collected.
 N = population size

k = size of interval
for selection

It requires a
random starting
point to avoid bias.
4 Cluster Sampling In this technique, Used for the Consider a scenario
the population is population which where a survey is to be
divided into is naturally conducted on access
heterogeneous grouped into to healthcare services
clusters or groups, clusters or in a city. To perform
where each cluster clusters can be cluster sampling,
consists of a wide easily defined. different clusters will
variety of elements, be formed for every
and then clusters neighborhood, then a
are selected few neighborhoods
randomly as will be selected as a
samples. sample.

In Non-Random Sampling, every unit of the population does not have an equal probability of
being chosen. This sampling technique is generally used when selection is based on certain
factors like availability, accessibility, and characteristics. The Non-Random Sampling techniques
can be categorized as below:

Table 2: Non-Random Sampling Techniques

# Sampling Technique Definition Example
1 Convenience In this technique, Consider a scenario where a
Sampling population units that are survey is to be conducted on
conveniently available smartphone usage. To perform
are selected as samples. Convenience Sampling,
samples will be chosen from
locations such as a coffee shop
or a shopping mall, as they are
conveniently available.
2 Judgment Sampling In this technique, Consider a scenario where a
samples are selected survey is to be conducted on
based on the the effectiveness of a new
 researcher’s judgement. teaching method. To perform
Judgment Sampling, an
educator selects students from
various grade levels based on
their academic strength and
motivation.
3 Quota Sampling In this technique, the Consider a scenario where a
population is divided into survey is to be conducted on
subgroups based on smartphone preference. To
certain characteristics. perform Quota Sampling, the
These subgroups are population will be divided into
referred to as quotas, quotas based on age, income,
and samples are chosen and education levels. Samples
based on the will then be selected until the
predetermined quotas. quotas are filled.
4 Snowball Sampling In this technique, Consider a scenario where a
samples are selected survey is to be conducted on
based on referrals from herbal medicine usage. Initially,
other respondents. a few patients who use these
medicines are interviewed, and
then they introduce more such
patients, leading to a snowball
sampling.

Key Takeaways
 This reading collateral provides necessary knowledge on the concept of population and
sample.
 Several sampling techniques are also explained with an example.