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

net/publication/335228347

Sampling typology and techniques

Article · January 2017

CITATIONS READS

16 22,748

5 authors, including:

Rajneesh Kumar Gautam Aman Mishra

Swedish University of Agricultural Sciences 8 PUBLICATIONS 89 CITATIONS
36 PUBLICATIONS 158 CITATIONS
SEE PROFILE
SEE PROFILE

Shubham Shukla

7 PUBLICATIONS 28 CITATIONS

SEE PROFILE

All content following this page was uploaded by Rajneesh Kumar Gautam on 18 August 2019.

The user has requested enhancement of the downloaded file.

 IJSRD - International Journal for Scientific Research & Development| Vol. 5, Issue 09, 2017 | ISSN (online): 2321-0613

Sampling Typology and Techniques

Saumya Verma1 Rajneesh K Gautam2 Spriha Pandey3 Aman Mishra4 Shubham Shukla5
1,3,4,5
Department of Statistics 2Department of Civil Engineering
1,3,4,5
Universityof Lucknow, Lucknow, India 2Babasaheb Bhimrao Ambedkar Central University,
Lucknow, India
Abstract— Sampling is the act, process, or technique of the population” [6]. All disciplines conduct research using
selecting a suitable sample, or a representative part of a sampling of the population as a method, and the definition is
population for the purpose of determining parameters or standard across these disciplines. Only the creative
characteristics of the whole population. Study the entire description of sampling changes for purposes of creating
population of those people, places, and things is an endeavour understanding. The standard definition always includes the
that most researchers do not have the time and/or money to ability of the research to select a portion of the population that
undertake. The idea of gathering data from a population is one is truly representative of said population.
that has been used successfully over the years and is called a
census. It was also used by the Ancient Egyptians “to obtain II. LITERATURE REVIEW
empirical data describing their subjects”. The purpose of this
paper is to describe sampling as a method of data collection, A. Distinguishing between a Sample and a Population:
its methodology and types. The term population means all members that meet a set of
Key words: Sampling, Data collection, Population, Census specifications or a specified criterion. For example, the
population of the India is defined as all people residing in the
I. INTRODUCTION India. The population of Uttar Pradesh means all people
living within the city’s limits or boundary. A population of
In past years, the idea of collecting data from the entire
inanimate objects can also exist, such as all automobiles
population was used by political entities to collect opinions manufactured in Lucknow in the year 2003. A single member
about potential political candidates. Census data collection is of any given population is referred to as an element. When
still very popular for collecting public opinion for political
only some elements are selected from a population, we refer
endeavours. Formost researchers, however, collecting data
to that as a sample; when all elements are included, we call it
from an entire population is almost impossible because of the
a census. Data derived from a sample are treated statistically.
amount of people, places, or things within the population.
Using sample data, we calculate various statistics, such as the
Taking a census Involves much time and money; something mean and standard deviation. These sample statistics
which most researchers do not have access to. To collect data summarize (describe) aspects of the sample data. These data,
on a smaller scale, researchers gather data from a portion or
when treated with other statistical procedures, allow us to
sample of the population. The purpose of this paper is to
make certain inferences. From the sample statistics, we make
describe sampling as a method of data collection. Probability
corresponding estimates of the population. Thus, from the
and non-probability sampling as well as the surrounding
sample mean, we estimate the population mean; from the
validity issues will be discussed. Sampling theory may be sample standard deviation, we estimate the population
adapted for content analysis, laboratory experiments and standard deviation.
participant observation [2]. ‘A sample is a proportion or
subset of a larger group called population. ‘A good sample is B. Types of Sampling:
a miniature version of the population of which it is a part – Researchers use two major sampling techniques: probability
just like it, only smaller’ [3] [4]. This definition of a sample sampling and non probability sampling. With probability
may appear self-sufficient, but raises fundamental issues sampling, a researcher can specify the probability of an
about the relationship of our research sample to a wider element’s (participant’s) being included in the sample. With
population. First, how do we define the ‘population’ in non probability sampling, there is no way of estimating the
relation to the particular context that we are studying? probability of an element’s being included in a sample.
Sometimes the ‘population’ will reflect our common-sense 1) Probability Sampling:
understanding of this term in the sense of the population of a Probability sampling provides an advantage because of
particular geographical area (e.g. a town, region or country). researcher’s ability to calculate specific bias and error in
But very often, in the study of contemporary religion, such regards to the data collected. Probability sampling is defined
populations do not necessarily map neatly onto a as having the “distinguishing characteristic that each unit in
geographical area. Sometimes a ‘religious’ population may the population has a known, nonzero probability of being
be situated in a specific location (e.g. a religious order or local included in the sample” [8].
congregation), but increasingly may take forms that do not a) Random Sampling:
map simply onto easily defined spaces (e.g. social Probability sampling is also referred to as random sampling
movements, on-line networks or people engaged in or representative sampling. The word random describes the
globalized transactions). Defining the wider population from procedure used to select elements (participants, cars, test
which a sample is taken therefore requires us to be explicit items) from a population. When random sampling is used,
about what the qualities or traits are that characterize that each element in the population has an equal chance of being
particular population [5]. The sample should be selected (Simple random sampling) or a known probability of
“representative in the sense that each sampled unit will being selected (stratified random sampling). The sample is
represent the characteristics of a known number of units in referred to as representative because the characteristics of a

All rights reserved by www.ijsrd.com 298

 Sampling Typology and Techniques
(IJSRD/Vol. 5/Issue 09/2017/072)

properly drawn sample represent the parent population in all random sampling that researchers face is that the population
ways. Simple random sampling requires that each member of list should be carefully examined for arrangement order [1].
the population have an equal chance of being selected (as is Babbie goes on to explain that “if the elements are arranged
the main goal of probability sampling). A simple random in any particular order, researcher should ascertain whether
sample is selected by assigning a number to each member in that order will bias the sample to be selected and should take
the population list and then “use a random number table to steps to counteract any possible bias”. Henry and Gary [8]
draw out the members of the sample”[7]. Simple random Expounds by describing that this issue arises when “the
sampling is often called straight random sampling. The population listing is arranged in cyclical fashion and the cycle
naming convention of this type of probability sampling coincides with the selection interval”. This problem can be
method is not indicative of the discipline but reliant upon the remedied by examining the list and making sure that the list
researcher or author of the various books and articles of names is not arranged in any type of order.
referenced. That is to say that these two terms are d) Cluster Sampling:
interchangeable and is not interdependent on a specific In cluster sampling, cluster, i.e., a group of population
discipline within academia. elements, constitutes the sampling unit, instead of a single
b) Stratified Random Sampling: element of the population [10]. Consider that we want to
This procedure known as stratified random sampling is also a estimate health insurance coverage in Lucknow city. We
form of probability sampling. To stratify means to classify or could take a random sample of 100 households (HH). In that
to separate people into groups according to some case, we need a sampling list of Lucknow HHs. If the list is
characteristics, such as position, rank, income, education, sex, not available, we need to conduct a census of HHs. The
or ethnic background. These separate groupings are referred complete coverage of Lucknow city is required so that all
to as subsets or Subgroups. It also includes defining sub- HHs are listed, which could be expensive. Furthermore, since
groups within the wider population and then sampling our sample size is small compared to the numbers of total
randomly or systematically within these to ensure that each HHs, we need to sample only few, say one or two, in each
sub-group is adequately represented in the sample. This block (subdivisions). Alternatively, we could select 5 blocks
approach is helpful when researchers wish to over-sample a (say the city is divided into 200 blocks), and in each block
particular sub-group within their population, e.g. studying interview 20 HHs. We need to construct HH listing frame
equal numbers of men and women in the sample to compare only for 5 blocks (less time and costs needed). Furthermore,
their responses even though the numbers of men and women by limiting the survey to a smaller area, additional costs will
may not be equal in the whole population. For a stratified be saved during the execution of interviews. Such sampling
random sample, the population is divided into groups or strategy is known as “cluster sampling.”The blocks are
strata. A random sample is selected from each stratum based “Primary Sampling Units” (PSU) – the clusters. The
upon the percentage that each subgroup represents in the households are “Secondary Sampling Units” (SSU).
population. Stratified random samples are generally more
accurate in representing the population than are simple
random samples. They also require more effort, and there is a
practical limit to the number of strata used. Stratified random
sampling is “one in which the population is divided into
subgroups or ‘strata,’ and a random sample is then selected
from each subgroup” [4]. When a few characteristics are
known about a population, stratified random sampling is
preferable because the population may be arranged in
subgroups and then a random sample may be selected from
each of these subgroups [1].
c) Systematic Random Sampling:
It includes (choosing units from the sampling frame by
selecting one unit by random and then each subsequent unit
at a standard range from that, i.e. every 10th unit on the list
after the initially chosen unit). Systematic random sampling Fig 2.1 Flow chart of cluster sampling (IIT Kanpur, NPTEL)
is usually preferred over simple random sampling in so far as It is important to note that with the method of cluster
it is more convenient for the researcher. This type of sampling, an additional sampling method resides. Multistage
probability sampling is also called ordinal sampling and sampling is used in cluster sampling. At least one reference
pseudo-simple random samples) [9]. Systematic random separated multistage sampling from cluster sampling as a
sampling includes “selection of sampling units in sequences probability sampling method [8]. Henry indicates that
separated on lists by the interval of selection. The selection of multistage sampling is an extension of cluster sampling
the sample from the population list is made by randomly whereas all others include within the method of multistage
selecting a beginning and choosing every nth name sampling as part of cluster sampling. Multistage sampling
(MacNealy 155). Frey et.al calls the interval used to select occurs when a researcher must cluster together certain groups
every nth name the sampling rate. Bobbie [1] defines the because a master list is not available but encounters a more
same as sampling interval. The most important element of complex design. It involves two stages: 1) Select clusters
systematic random sampling is that the selection starting randomly from the population and list, and 2) Select
point is random. One inherent disadvantage to systematic

All rights reserved by www.ijsrd.com 299

 Sampling Typology and Techniques
(IJSRD/Vol. 5/Issue 09/2017/072)

individuals randomly from the clusters [2, 9]. While of procuring a sample that will represent the population they
multistage is a part of cluster sampling in most of the books are interested in learning about. In the example above, the
researched, not all see it as one method. interest is in people who have had their hair cut recently. The
2) Non- Probability Sampling: researcher would get far less results from those people exiting
The advantage of non-probability sampling is that it a a restaurant. While some of those people may have had their
convenient way for researchers to assemble a sample with haircut that day, the better selection is to go to a place where
little or no cost and/or for those research studies that do not haircuts take place.
require representativeness of the population [1]. Non- b) Purposive:
probability sampling is a good method to use when It is also known as judgemental sampling, purposive
conducting a pilot study, when attempting to question groups sampling is a non-probability technique that involves the
who may have sensitivities to the questions being asked and conscious selection by the researcher of certain people to
may not want answer those questions honestly, and for those include in a study. Participants are selected because they have
situations when ethical concerns may keep the researcher particular characteristics that are of interest to the researcher.
from speaking to every member of a specific group [11]. For example, they have had the experience in which the
Author Type of Non- Probability Sampling researchers are interested, or there are certain aspects of their
Purposive or judgmental sampling lives in which the researchers are interested. Purposive
Quota sampling sampling is selecting a sample “on the basis of your own
Babbie, et al. knowledge of the Population, its elements, and the nature of
Reliance of available subjects
(Convenience) your research aim” [2] i.e. the population is “non-randomly
Convenience selected based on a particular characteristic” [9]. The
Snowball sampling individual characteristics are selected to answer necessary
Fink, et al. questions about a “certain matter or product” [7]. The
Quota sampling
Focus groups researcher is then able to select participants based on internal
Convenience knowledge of said characteristic. This method is useful if a
Volunteer researcher wants to study “a small subset of a larger
Frey, et al. Purposive population in which many members of the subset are easily
Quota identified but the enumeration of all is nearly impossible” [2].
Network (snowball) Pilot studies are well suited to this type of non-probability
Conveniences samples sampling method.
Most similar/most dissimilar samples c) Snowball:
(purposive) This particular one identifies, cases of interest from people
Henry, et al. Typical case samples (purposive) who know people, who know what cases is information rich
Critical case samples (purposive) that is good examples for study, or good interview subjects.
Snowball samples This is commonly used in studies that may be looking at
Quota samples issues like the homeless households. What you do is to get
Convenience sampling hold of one and he/she will tell you where the others are or
MacNealy, et can be found. When you find those others they will tell you
Purposeful sampling
al. where you can get more others and the chain continues.The
Snowball sampling
Table 2.1: Various Non-probability Sampling Methods by researcher builds their sample on the basis of contacts
Author suggested by other participants. This potentially has the
advantage of drawing on participants’ own expertise in
a) Convenience: developing the sample as well as expanding the sample
The sample is selected primarily on the basis of what the beyond contacts known to the researcher in the first stage of
researcher is able to access. Whilst this is often a default their project. Snowball sampling is a type of non-probability
approach in small-scale pieces of research (e.g. sampling technique. Non-probability sampling focuses on
undergraduate or Masters’ dissertations which may rely on sampling techniques that are based on the judgement of the
the writer’s existing contacts), one of the strongest rationales researcher. Some populations that we are interested in
for this method is when the group or phenomenon under study studying can be hard-to-reach and/or hidden. These include
is generally difficult to access but the researcher is able to populations such as drug addicts, homeless people, and
establish a sufficient degree of contact or trust with particular individuals with AIDS/HIV, prostitutes, and so forth. Such
participants to conduct a viable project [5]. For example, populations can be hard-to-reach and/or hidden because they
convenience sampling may include going to a place of exhibit some kind of social stigma, illicit or illegal
business (mall, restaurant, etc.) and questioning or surveying behaviours, or other trait that makes them atypical and/or
those people who are available and consent to being socially marginalized. Snowball sampling is a non-
questioned. If the researcher is interested in what people think probability based sampling technique that can be used to gain
of hair cutting techniques from a consumer perspective, the access to such populations. Snowball sampling is a useful
researcher may go to a hair salon and a Barber shop and poll choice of sampling strategy when the population you are
those patrons leaving the establishment after getting their hair interested in studying is hidden or hard-to-reach. Snowball
cut.While convenience sampling includes only those ready sampling may also be viewed as an effective sampling
and available, there is no excuse for sloppiness [2]. Babbie strategy from a perspective of research design and the choice
goes on to explain that “survey researchers need to find ways of research methods. Whilst the use of quantitative research

All rights reserved by www.ijsrd.com 300

 Sampling Typology and Techniques
(IJSRD/Vol. 5/Issue 09/2017/072)

designs, surveys methods, and statistical analyses are geared [9] Frey, Lawrence, Carl, Investigating communications,
towards the use of probability-based sampling techniques that 2000
make it possible to draw statistical inferences from a sample [10] Ocw.jhsph.edu/courses/StatMethodsForSampleSurveys/
that can be generalised to a population. PDFs/Lecture5.pdf
d) Quota: [11] Fink, Arlene. How to Sample in Surveys. Vol. 6.
Quota sampling is a non-probability sampling technique London: Sage Publications, 1995
wherein the assembled sample has the same proportions of
individuals as the entire population with respect to known
characteristics, traits or focused phenomenon. In addition to
this, the researcher must make sure that the composition of
the final sample to be used in the study meets the research's
quota criteria. In a study wherein the researcher likes to
compare the academic performance of the different high
school class levels, its relationship with gender and
socioeconomic status, the researcher first identifies the
subgroups. Usually, the subgroups are the characteristics or
variables [4] of the study. The researcher divides the entire
population into class levels, intersected with gender and
socioeconomic status. Then, he takes note of the proportions
of these subgroups in the entire population and then samples
each subgroup accordingly. The main reason why researchers
choose quota samples is that it allows the researchers to
sample a subgroup that is of great interest to the study. If a
study aims to investigate a trait or a characteristic of a certain
subgroup, this type of sampling is the ideal technique.

III. CONCLUSION
In conclusion, it can be said that using a sample in research
saves mainly on money and time, if a suitable sampling
strategy is used; appropriate sample size selected and
necessary precautions taken to reduce on sampling and
measurement errors, then a sample would yield valid and
reliable information. Researchers may choose from a variety
of sampling methods. The researcher’s goals inform which
sampling method is best for the research to be conducted. The
main choice in regards to sample method choice is whether
or not the researcher wants to generalize the findings from the
sample to the whole of the population being studied. Being
aware of possible errors due to the sample method chosen is
also very important because giving possible errors within the
results section allows the study to be regarded as valid. Many
sample method choices are available; the researcher must
choose the method that is right for the study.

REFERENCES
[1] Bobbie Latham, Quantitative research methods, ENGL
5377, Spring March 2007.
[2] Babbie, Earl. Survey Research Methods, Belmont,
California, 1990
[3] http://trochim.human.cornell.edu/tutorial/mugo/tutorial.
htm (11 of 11) [9/6/2002.
[4] Fink, A. (2003) How to Sample in Surveys. 2nd Edition.
Thousand Oaks: Sage.
[5] Gordon Lynch, Oxford Seminar, 2007
[6] Lohr, Sharon L. Sampling: Design and Analysis. Albany:
Duxbury Press, 1999.
[7] MacNearly, Mary Sue, Strategies of empirical research
in writing, New york, 1999
[8] Henry, Gary T. Practical Sampling. Vol. 21. London:
Sage Publications, 1990

All rights reserved by www.ijsrd.com 301

View publication stats