See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/371985672

Sampling Methods in Research: A Review

Article · June 2023

CITATIONS READS

4 2,585

4 authors, including:

Dhaval Makwana Priti Engineer

12 PUBLICATIONS 25 CITATIONS
Institute of Teaching & Research In Ayurveda - Jamnagar
10 PUBLICATIONS 25 CITATIONS
SEE PROFILE
SEE PROFILE

Hardik Chudasama
National Institute of Ayurveda
23 PUBLICATIONS 28 CITATIONS

SEE PROFILE

All content following this page was uploaded by Dhaval Makwana on 02 July 2023.

The user has requested enhancement of the downloaded file.

 International Journal of Trend in Scientific Research and Development (IJTSRD)
Volume 7 Issue 3, May-June 2023 Available Online: www.ijtsrd.com e-ISSN: 2456 – 6470

Sampling Methods in Research: A Review

Dhaval Makwana1, Priti Engineer2, Amisha Dabhi3, Hardik Chudasama4
1
Assistant Professor, Ayurved Samhita & Siddhanta Department,
Indian Institute Ayurveda Research, Ishwariya-Rajkot, Gujarat, India
2
Ph.D. Scholar, Department of Shalya tantra, Institute of Teaching & Research in Ayurveda, Jamnagar, Gujarat, India
3
PG Scholar, Ayurved Samhita & Siddhanta Department, National Institute of Ayurveda, Jaipur Rajasthan, India
4
Ph.D. Scholar, Kriya Sharir Department, National Institute of Ayurveda, Jaipur, Rajasthan, India

ABSTRACT How to cite this paper: Dhaval

The accuracy of a study is heavily influenced by the process of Makwana | Priti Engineer | Amisha
sampling. The article provides an overview of the various sampling Dabhi | Hardik Chudasama "Sampling
techniques used in research. These techniques can be broadly Methods in Research: A Review"
categorised into two types: probability sampling techniques and non- Published in
International Journal
probability sampling techniques. Probability sampling techniques
of Trend in
include simple random sampling, systematic random sampling, and Scientific Research
stratified random sampling. On the other hand, non-probability and Development
sampling techniques include quota sampling, self-selection sampling, (ijtsrd), ISSN: 2456-
convenience sampling, snowball sampling, and purposive sampling. 6470, Volume-7 | IJTSRD57470
Issue-3, June 2023,
KEYWORDS: Cluster, Medical statistics, Sampling, Snowball pp.762-768, URL:
www.ijtsrd.com/papers/ijtsrd57470.pdf

Copyright © 2023 by author (s) and

International Journal of Trend in
Scientific Research and Development
Journal. This is an
Open Access article
distributed under the
terms of the Creative Commons
Attribution License (CC BY 4.0)
(http://creativecommons.org/licenses/by/4.0)

INTRODUCTION
The term "research" has its origins in the Middle question. [3] Research can be regarded as a means of
French language, specifically from the word augmenting the current body of knowledge, thereby
"recherche", which translates to "to go about enhancing its sophistication. The primary aim of
seeking". This word is derived from the Old French research is to systematically acquire knowledge or
term "recerchier", which is a combination of "re-" and ascertain solutions to inquiries through scientific
"cerchier" or "sercher", meaning "search". The methodologies.
earliest recorded use of the term was in 1577.[1]
Some of the general objectives of research are as
Definition of Research: According to Clifford follows:
Woody, research comprises defining and redefining 1. To know about a subject or to find out something
problems; formulating hypothesis or suggested new in that – exploratory or formulative research
solutions; collecting, organizing, and evaluating the 2. To know about the subject in depth, for example,
data; making deductions and reaching conclusions; the characteristics, nature of a particular group, or
and at last, carefully testing the conclusions to individual-descriptive research
determine whether they fit the formulating 3. To correlate the association of some particulars
hypothesis. [2] definition of research is given by John with something else – diagnostic research
W. Creswell, who states that “research is a process of
There are different types of research; some of them
steps used to collect and analyze information to
are listed below:
increase our understanding of a topic or issue”. It Descriptive and analytical
consists of three steps: pose a question, collect data to Applied and fundamental
answer the question, and present an answer to the

@ IJTSRD | Unique Paper ID – IJTSRD57470 | Volume – 7 | Issue – 3 | May-June 2023 Page 762
 International Journal of Trend in Scientific Research and Development @ www.ijtsrd.com eISSN: 2456-6470
Quantitative and qualitative Materials and Methods:
Conceptual and empirical Information on Sampling methods was collected from
Other types include clinical, historical, and different books of medical research methodology and
conclusion oriented. peer reviewed journal.
The research process can be facilitated by following a Result and Discussion:
set of procedural guidelines that encompass various Defining sampling: Sampling is the process of
steps. Some of these steps include: choosing a sample of a population from an individual
1. Formulating the research problem or a large group for a certain type of research
2. Extensive literature survey objective. The use of sampling has a variety of
3. Hypothesis developing benefits and drawbacks. We might occasionally
4. Preparing research design wonder, "Why is sampling necessary?" The reason
5. Determining the sample size we employ sampling is because it would be extremely
6. Collecting the data expensive and time-consuming to survey the entire
7. Execution of the project population for a research study. [4] [5] [6]
8. Analysis of data Types of sampling: A sample is a collection of
9. Hypothesis testing individuals, things, or things collected from a large
10. Generalization and interpretation population for measurement in research. So sampling
11. Preparation of report or presentation of the results
is done in order to obtain accurate data. [7] To
As per the aforementioned procedures, it is examine whether all the chips in a factory are good or
imperative to formulate the research design and not, for instance, would be quite challenging. Instead,
ascertain the appropriate sample size in order to we would choose a random chip and assess its
conduct comprehensive research. Therefore, we will flavour, shape, and size. Therefore, sampling is a
thoroughly examine the various sampling techniques critically important research method when there is a
or sample designs. huge population. Due of this, we have separated it
into two categories: Probability and nonprobability. [8]

Image-1: Type of Sampling

[9]
Probability sampling:
In probability sampling, every member of the population has a predetermined chance of being chosen for
inclusion in the sample. In cases where the population exhibits a high degree of homogeneity, the likelihood of
any given member being selected in a sample is significantly increased. In a scenario where a bag is filled with
rice, the likelihood of selecting each individual grain of rice in a sample is considerably high. Therefore, the
collected sample will be indicative of the entire contents of the rice bag. In the context of this study, the
population is considered to be relatively homogeneous due to the fact that each member of the population is a
potential respondent for the research.

@ IJTSRD | Unique Paper ID – IJTSRD57470 | Volume – 7 | Issue – 3 | May-June 2023 Page 763
 International Journal of Trend in Scientific Research and Development @ www.ijtsrd.com eISSN: 2456-6470

Image-2: Type of Probability Sampling

Simple random sampling is a method of selecting a sample from a population in which each member of the
population has an equal chance of being selected. This technique is commonly used in research studies to ensure
that the sample is representative of the population and to minimise bias. By randomly selecting participants,
researchers can increase the likelihood that their findings will be generalizable to the larger population. In this
sampling methodology, the selection of sample members is based solely on chance and randomization.
Consequently, the sampling process ensures that the sample quality remains unaffected, as each member of the
population has an equal probability of being chosen for inclusion in the sample. This sampling method is most
suitable for a population that exhibits a high degree of homogeneity. There exist two distinct methodologies for
conducting this particular form of sampling: The lottery method, also known as the envelope method, is a
technique used to allocate resources or distribute tasks among a group of individuals. The present approach
involves the allocation of distinct numerical values to individual constituents or entities within the populace. For
instance, in a population comprising 100 members, ordinal numbers ranging from 1 to 100 are designated to
each member and inscribed on a piece of paper, which is subsequently deposited in a receptacle. Subsequently, a
chit will be extracted, and the numerical value inscribed on it will represent a randomised sample. Nonetheless,
in this approach, the task of inscribing the name of each number on the chits becomes challenging as the
population size increases. Therefore, an alternative approach is employed, namely the utilisation of a random
number table (which will be further elaborated upon subsequently). An additional illustration provided involves
the utilisation of an envelope method. For instance, in a research endeavour aimed at selecting patients with
Hypertension for participation in yoga, this approach may be employed. Each envelope will contain the details
of 100 patients, and a random selection will be made from among them. Therefore, in this context, the
probability of all patients being selected as a sample is equivalent.
The random number table method is a statistical technique used to generate random numbers for research
purposes. This method involves using a table of random digits to select numbers at random, which can then be
used in various statistical analyses. The random number table method is commonly used in experimental design,
survey research, and other areas of social science research. Various random tables are accessible, including
Fisher's and Yates' tables, as well as Tippet's random number table. Initially, numerical values are assigned to the
population in this context. In the scenario where there is a population of 20 and a sample of five is required, a
random selection of five numbers from the table must be made. As an illustration, a selection comprising the
integers -12, 19, 01, 08, and 15 is made. Therefore, individuals belonging to these numerical categories will be
chosen as the sample.
The preceding section has expounded upon the techniques employed in conducting a simple random sampling.
This section will cover the various types of simple random sampling. The methodology of selecting a sample
from a population using a random process, whereby each member of the population has an equal chance of being

@ IJTSRD | Unique Paper ID – IJTSRD57470 | Volume – 7 | Issue – 3 | May-June 2023 Page 764
 International Journal of Trend in Scientific Research and Development @ www.ijtsrd.com eISSN: 2456-6470
selected and the selection is made with replacement, is referred to as simple random sampling with replacement.
The process of choosing "n" units from a total of "N" units, one at a time, is referred to as random sampling.
This method ensures that each unit has an equal probability of being selected at each stage of the selection
process, which is 1/N. The method of selecting a sample from a population in which each member has an equal
chance of being chosen, without replacing the selected member back into the population, is known as simple
random sampling without replacement. The process of selecting a sample involves choosing "n" units from a
total population of "N" units, one at a time. It is important to ensure that at any stage of the selection process,
each remaining unit has an equal probability of being chosen, which is 1/N. Suppose we seek to determine the
population of turtles inhabiting a village pond. If we opt to capture turtles from the pond, measure them, and
subsequently release them back into the water, we run the risk of selecting the same turtle multiple times. This
scenario is indicative of a simple random sampling with replacement (SRSWR) methodology. Nevertheless, if
the turtle is removed from the aquatic environment and not reintroduced until another turtle is taken, the
situation can be classified as SRSWOR.
Stratified random sampling is a statistical technique that involves dividing a population into subgroups or strata
based on certain characteristics, and then selecting a random sample from each stratum. This method is
commonly used in research studies to ensure that the sample is representative of the population and to increase
the precision of the estimates. By stratifying the population, the variability within each stratum is reduced, which
can lead to more accurate results. Overall, stratified random sampling is a valuable tool for researchers seeking
to obtain a representative sample from a larger population.
Proportionate stratified sampling is a statistical sampling technique that involves dividing a population into
subgroups or strata based on certain characteristics, and then selecting a proportional number of individuals from
each stratum to be included in the sample. This method is commonly used in research studies to ensure that the
sample accurately represents the population being studied.
Proportionate stratified sampling is a sampling technique where the sample size allocated to each stratum is
proportional to the size of the stratum relative to the entire population. Upon determining the sample size,
researchers proceed to compute the percentage or proportion of each stratum in relation to the size of the target
population. After determining the relative size of each stratum, it is possible to establish a sample size for each
stratum. Upon completion of the aforementioned step, the technique of simple random sampling may be
employed to randomly select elements from each respective stratum. The aforementioned sampling technique is
comparatively less complex, time-efficient, and direct in contrast to disproportionate stratified sampling. The
utilisation of this approach is motivated by the observation that larger strata or subpopulations exhibit greater
standard deviations with respect to the selected stratified variables. Consequently, in order to enhance the
accuracy of the investigation, it is imperative to select larger sample sizes from these strata.
Disproportionate stratified sampling is a sampling technique that involves dividing a population into strata based
on certain characteristics and then selecting a sample from each stratum in a manner that is not proportional to
the size of the stratum. Disproportionate stratified sampling involves selecting a sample size from each stratum
that is proportional to both the stratum's relative size and the standard deviation in the distribution of
characteristics among the elements within that stratum. The selection of sample units from each stratum is based
on the researcher's discretion and the underlying rationale of their study.
Systematic sampling is a statistical sampling technique that involves selecting a sample from a larger population
using a predetermined interval. This method ensures that every nth member of the population is included in the
sample, resulting in a representative subset of the population. Systematic sampling is commonly used in research
studies and surveys to obtain a sample that is both efficient and unbiased. Systematic sampling is a sophisticated
variant of the simple random sampling technique that requires comprehensive information pertaining to the
population. In this process, a member is chosen at regular intervals. The selected individual will henceforth be
referred to as the Kth element.
Linear systematic sampling is a statistical sampling technique that involves selecting every kth element from a
list or population after a random starting point has been determined. This method is commonly used in research
studies to obtain a representative sample of a larger population. The entire population list is sequentially
compiled into a list. The determination of sample size and calculation of sampling interval can be achieved
through the use of a specific formula. The formula K = N/n represents the Kth element, where N denotes the
entire population and n represents the number of samples. Select a random integer within the range of 1 to K,
and subsequently add K to the selected integer to obtain the subsequent sample.

@ IJTSRD | Unique Paper ID – IJTSRD57470 | Volume – 7 | Issue – 3 | May-June 2023 Page 765
 International Journal of Trend in Scientific Research and Development @ www.ijtsrd.com eISSN: 2456-6470
The methodology of circular systematic sampling involves the initial determination of the sample interval,
followed by the selection of the number closest to the ratio of N/n. Suppose that N equals 17 and n equals 4. In
this scenario, the value of k is considered to be 4 instead of 5. The selection process involves choosing units
randomly from the range of 1 to N, while skipping K units after each selection until a total of n units have been
chosen. In this particular type of sampling, the number of samples N is greater than the number of samples K
found in linear systematic sampling.
Cluster sampling involves partitioning a population into clusters, from which a random sample of members is
selected. Cluster sampling and stratified sampling are distinct sampling techniques. Stratified sampling involves
the division of a population into subgroups based on characteristics such as age, sex, and profession. On the
other hand, cluster sampling entails the random selection of pre-existing or naturally occurring groups or
clusters, such as towns within a district or families within a society. In an urban setting, identifying a
comprehensive roster of individuals afflicted with HBsAg can prove challenging. However, by conducting a
search according to geographical regions, more favourable outcomes may be achieved. In this context, the region
functions as a cluster and the individuals are regarded as sampling units. This approach involves the formation of
clusters based on specific criteria, followed by the selection of a sample through either simple random sampling
or systematic sampling techniques.
Multi-stage sampling, also referred to as multi-stage cluster sampling, is a sophisticated variant of cluster
sampling that involves the selection of samples in two or more stages. Multi-stage sampling is a technique used
to facilitate primary data collection by dividing large clusters of population into smaller clusters through several
stages. It is imperative to recognise that multi-stage sampling, while not as efficacious as true random sampling,
does mitigate certain drawbacks inherent in the latter approach, such as excessive cost and time consumption.
Despite its nomenclature, the implementation of multi-stage sampling in business research can be
straightforward. The utilisation of this sampling technique can be categorised into four distinct phases. The
process of selecting a representative subset of discrete groups involves several steps, including the careful
selection of a sampling frame, the assignment of unique numerical identifiers to each group, and the subsequent
selection of a small but relevant sample. The process of selecting a sampling frame that comprises pertinent
discrete sub-groups. This task ought to be carried out utilising pertinent distinct groups that were chosen in the
preceding phase. If deemed necessary, the second stage should be repeated. The process of selecting individuals
for the sample group involves utilising a form of probability sampling to draw from the sub-groups. The
practical implementation of the aforementioned stages can be demonstrated through a particular instance. The
aim of the study is to assess the online expenditure habits of American households by means of online surveys.
One possible approach for forming a sample group of 120 households is as follows, select six states in the
United States of America utilising a method of probability sampling such as simple random sampling. Utilise a
systematic sampling technique, or any other form of probability sampling, to select four districts from each state.
Select a sample of five households from each district utilising either simple random or systematic sampling
techniques. The inclusion of 120 households in the sample group will ensue.
Nonprobability Sampling: [10]
Nonprobability sampling is a sampling technique in which the likelihood of each member of the population
being selected for the sample is not known. To investigate the effects of child labour on minors, the researcher
will exclusively seek out and conduct interviews with children who have been exposed to such labour practises.
In purposive sampling, individuals are chosen for inclusion in a sample based on their relevance to the research
objectives. The term "deliberate sampling" is also commonly utilised. This sampling technique is alternatively
referred to as judgmental sampling. To investigate the effects of yoga on individuals with Hypertension, it is
recommended that only hypertensive patients be selected as the most suitable participants. Including individuals
with other forms of heart disease may not yield optimal results for this study. Therefore, the investigator
intentionally chooses exclusively individuals diagnosed with hypertension as participants for the present
investigation.
The act of choosing sample members based on their ease of accessibility is referred to as convenience sampling.
The selection process involves choosing members who are readily available to the researcher. This sampling
method utilises the existing data without imposing any additional criteria. This is a more prevalent practise in
pilot testing. The study's participants or samples are chosen based on their ease of recruitment.
Snow‑ball sampling method is commonly referred to as chain sampling or sequential sampling, and is employed
when a respondent recruit additional respondents from their personal network, such as friends, relatives, or

@ IJTSRD | Unique Paper ID – IJTSRD57470 | Volume – 7 | Issue – 3 | May-June 2023 Page 766
 International Journal of Trend in Scientific Research and Development @ www.ijtsrd.com eISSN: 2456-6470
acquaintances. This type of sampling is utilised in scenarios where the identification of sample members is
challenging. As an illustration, a scholar intends to investigate the challenges encountered by migrant
populations within a given locality. The researcher will initiate the sampling process by selecting one migrant,
who will then provide information about another migrant. This will create a chain effect, resulting in a snowball-
like growth of the sample. The researcher will continue this method until the desired sample size is attained.
There are three patterns of snowball sampling. Linear snowball sampling is a technique that Only one subject
and one referral are provided by the subject for forming a sample group. The referral is added to the sample
group and contributes just one additional referral. Up until the sample group is complete, this procedure is
followed. Exponential Non-Discriminative Snowball Sampling The first participant chosen for the sample group
contributes numerous recommendations. Every new referral is investigated until enough primary data from
samples are gathered. Exponential discriminative snowball sampling is a technique. Multiple recommendations
from subjects are received, but only one new subject is chosen from them. The purpose and goals of the study
serve as a guide when selecting a new subject.

Image-3: Type of Snowball Sampling

In quota sampling, participants are picked based on a Conclusion:
set of predetermined criteria that the researcher has Sampling techniques are essential to research and
established. These particular traits work as a quota for data analysis because they allow us to infer important
choosing the sample's participants. We acquire information about vast populations from a smaller
representative data from a group via this kind of group of data. Each sampling technique, including
sampling. It is comparable to probability sampling simple random sampling, stratified sampling, cluster
techniques like stratified random sampling. The sole sampling, and systematic sampling, has advantages
distinction between the two is that whereas quota and disadvantages. To choose the best sampling
sampling does not use random selection, stratified strategy, researchers must carefully assess their
random sampling does. In a well-planned manner, the study's goals, the population's characteristics, and the
participants are divided into specified categories, such resources at their disposal. Researchers can increase
as 100 men and 100 women. It comes in two flavours: the validity and dependability of their findings by
controlled quota sampling, where the researcher's using sound sampling techniques, thereby advancing
options are constrained. The alternative type is knowledge in a variety of domains.
uncontrolled quota sampling, where there are no
restrictions and samples are chosen based on the
research's convenience.

@ IJTSRD | Unique Paper ID – IJTSRD57470 | Volume – 7 | Issue – 3 | May-June 2023 Page 767
 International Journal of Trend in Scientific Research and Development @ www.ijtsrd.com eISSN: 2456-6470
References: 2012. p. 125-74. Avaliable on:
[1] Definition of RESEARCH. (2023, May 29). https://www.academia.edu/30353662/Sampling
Research Definition & Meaning - Merriam- _methods_in_Clinical_Research_an_Education
Webster. https://www.merriam- al_Review.
webster.com/dictionary/research.
[6] Teddlie C, Yu F. Mixed methods sampling: A
[2] Clifford Woody Research Method - 1116 Words typology with examples. J Mix Methods Res
| Internet Public Library. (n.d.). Clifford 2007; 1:77-100.
Woody Research Method - 1116 Words |
[7] Joseph F. Hair Jr. William C. Black Barry J.
Internet Public Library.
Babin Rolph E. Anderson Multivariate Data
https://www.ipl.org/essay/The-Importance-Of-
Analysis 7th edition. Pearson Education
Qualitative-Research-Method-
Limited; England 2014
F3LBCJYKRJ4DR
[8] Saunders MN, Saunders M, Lewis P, Thornhill
[3] Creswell, J.W. (2008). Educational Research:
A. Research Methods for Business Students.
Planning, conducting, and evaluating
5th Edition, Pearson Education, Essex 2011.
quantitative and qualitative research (3rd ed.).
Upper Saddle River: Pearson. [9] Indrayan A. Research Methods for Medical
Graduates. CRC Press; 2019. p.197-206
[4] Elfil M, Negida A. Sampling methods in
clinical research; an educational review. [10] Kumar R. Research Methodology: A Step-By-
Emergency. 2017;5 Step Guide for Beginners. 2005. p.147-150.
https://doi.org/10.1604/9781412911948
[5] Sampling P, Guidelines P, Choices MS, Oaks
T. Choosing the Type of Sampling. Ch. 5.

@ IJTSRD | Unique Paper ID – IJTSRD57470 | Volume – 7 | Issue – 3 | May-June 2023

View publication stats
Page 768