RESEARCH METHODS and

COMPUTER APPLICATIONS

TERM PAPER ON
METHODS OF STUDY –
SAMPLING METHODS
SAMPLING
Sampling is that part of statistical practice concerned with the
selection of an unbiased or random subset of individual observations
within a population of individuals intended to yield some knowledge about the
population of concern, especially for the purposes of making
predictions based on statistical inference. Sampling is an important
aspect of data collection.

Researchers rarely survey the entire population for two reasons (Adèr,
Mellenbergh, & Hand, 2008): the cost is too high, and the population
is dynamic in that the individuals making up the population may
change over time. The three main advantages of sampling are that the
cost is lower, data collection is faster, and since the data set is smaller
it is possible to ensure homogeneity and to improve the accuracy and
quality of the data.

A sample is a smaller representation of a larger whole. The

observation of some phenomena in complete detail would involve
such a mass of data that analysis would be slow and tedious.
Moreover, to analyze large quantities of material is wasteful when a
smaller amount would suffice.

Thus, the use of sampling allows for more adequate scientific work by
making the time of the scientific worker count. Another obvious value
of sampling is that it also saves money and thus makes investigations
possible which could not otherwise be undertaken.

FUNDAMENTAL CONCEPTS
1. POPULATION : The term research population is used to refer to all
members of the group of interest to the researcher. For example, if a
sociologist is interested in researching women’s experiences of the
labour market, the research population will consist of all women who
work. However, it is clear that this group would be too big for the
researcher to incorporate into his or her study, so the researcher
selects a smaller group of individuals from this larger target group.
2. SUB POPULATION OR POPULATION STRATUM: A further sub
division of a population. for example, married males within the
population defined above would constitute a sub population.
3. SAMPLE: Sample is the term used to refer to the smaller group of
individuals selected from the target population for the purpose of
study. According to coolican, a sample might not consist of people .
for example, a biologist might be interested in studying the quality of
cabbages in one field. In this case a number of cabbages would be
chosen to from the research sample, and all the cabbages in the field
would comprise the research population.
4. CENSUS : A count, taken at one time, of the total population.

5. SAMPLING FRAME : For sampling to be representative it is

necessary to obtain or develop a comprehensive list of the individuals
that make up the target population. This list is known as the sampling
frame. This is because only individuals on that list are relevant to the
research and hence from a logical group from which to select the
sample. If the list is incomplete or inaccurate, the sample may not
reflect the target population.
6. SAMPLE SIZE: it is important for the researcher to give careful
consideration to the size of sample to be used in the study. Small
samples may lead to biased results because there is a greater chance
of disproportionate representation. Larger sample sizes can reduce
the chance of sampling bias and the findings are likely to be more
accurate. Professional sociologists vary their sample size according to
the purpose of their research.
TYPES OF SAMPLING
Sampling is of 2 types: PROBABILITY AND NON PROBABILITY
SAMPLING. Probability sampling permits the researcher to specify
for each case or individual in the population the probability of that
item’s inclusion in the sample.

Example: We want to estimate the total income of adults living in a

given street. We visit each household in that street, identify all adults
living there, and randomly select one adult from each household. We
then interview the selected person and find their income. People
living on their own are certain to be selected, so we simply add their
income to our estimate of the total. But a person living in a household
of two adults has only a one-in-two chance of selection. To reflect
this, when we come to such a household, we would count the selected
person's income twice towards the total.

In the above example, not everybody has the same probability of

selection; what makes it a probability sample is the fact that each
person's probability is known

Non probability sampling lacks this characteristic and, thus, there are
no assurances that each case had some chance of being included in the
sample.

Example: We visit every household in a given street, and interview

the first person to answer the door. In any household with more than
one occupant, this is a nonprobability sample, because some people
are more likely to answer the door (e.g. an unemployed person who
spends most of their time at home is more likely to answer than an
employed housemate who might be at work when the interviewer
calls) and it's not practical to calculate these probabilities.

There are three basic types of non probability sampling:

ACCIDENTAL, QUOTA SAMPLING, and PURPOSIVE
SAMPLING.
1. ACCIDENTAL SAMPLING: Such samples are selected generally for
sheer availability and lack of expense. There is no way to evaluate
biases in an accidental sampling.
2. QUOTA SAMPLING: This involves identifying specific qualities of
characteristics in the target population and classifying them into
categories. A sample is then drawn that consist of a specified number
of subjects for each category. Commonly used by market researchers,
the technique involves ascertaining which categories individuals fit
and obtaining data from them. Data collection stops when all the
information required has been collected from the specified number of
individuals, for example, 10 men, 10 women, 10 boys, 10 girls and so
on.
3. PURPOSIVE SAMPLING: These samples are based on individually
selected cases. The cases may be selected due to their unique
character or their availability. For example, the persons convicted of
murder in a given judicial district might be the basis on an interesting
purposive sample.
There are three basic types of probability sampling: SIMPLE
RANDOM SAMPLING, STRATIFIED RANDOM SAMPLING
AND CLUSTER SAMPLING.
1. RANDOM SAMPLING: A random sample is a sample in which all
members of the population have an equal chance of being selected. It
is very hard to arrive at a truly random sample. The larger the target
group to be studied, the harder it becomes. Researchers cannot rely on
volunteers because this erodes the ‘unpredictable’ nature of random
sampling. There would be systematic inclusion of those who were
willing to put themselves forward.
TECHNIQUES FOR RANDOM SAMPLING
a. MANUAL SELECTION: This is well demonstrated by the system
used to select the numbers in national lottery draws. Set numbers are
placed into a container, shuffled and picked out. Crucially, all the
numbers are invisible to the selector and there is no way of predicting
which will be chosen. Other examples of this technique include
numbers out of a hat, numbered bingo balls selected by a blast of air
and so on.
b. RANDOM NUMBER TABLES: This involves using a set of random
number tables to select a sample. Because the numbers are generated
at random, it is possible to move horizontally or vertically along the
lines of the tables to pick a series of numbers.

c. COMPUTER GENERATED SAMPLES: The names of the individuals

in the target population are typed into the computer and the random
number programme is used to generate a random list of individuals to
make up the research sample.
2. STRATIFIED RANDOM SAMPLING: This is a special kind of
sampling where the target population is divided into strata or layers,
for example, according to social class, age, or family income. A
number of people from each layer are separately chosen to represent
their stratum in the study. This ensures that all important groups are
represented independently. This can reduce time, effort and cost by
allowing smaller sample sizes. For example, poverty is known to be
most common among the elderly, the unemployed and single parent
families, so research on the effects of poverty might well sample each
of these three strata separately as part of a survey of poverty in the
population as a whole , which would permit the total sample size to be
reduced because the investigator would know that the groups most
affected by poverty are guaranteed inclusion.
3. CLUSTER SAMPLING: In a large scale survey, this is often cheaper
and easier than simple or stratified random selection. The sampling
plan first calls for random selection of cluster either simple or
stratified random sampling. Then all the cases within a cluster are
used or random selection within each selection within each selected
cluster may be desired.

A particular design may call for a combination of probability and non

probability sampling. For example, a design might call for an
experimental group (selected randomly) and a control group matched
on key characteristics to the experimental group (purposive).

PROCESS
The sampling process comprises several stages:

 Defining the population of concern

 Specifying a sampling frame, a set of items or events possible to
measure
 Specifying a sampling method for selecting items or events from
the frame
 Determining the sample size
 Implementing the sampling plan
 Sampling and data collecting

Sampling of any kind is not always necessary. Particularly an applied

research, it may be possible to obtain responses from the entire
population. If one wishes to know, only about this population, then
sampling is not an issue. Census data is of this type and includes the
whole population. Samples may then be drawn from the census data,
if smaller numbers are desired.

REFERENCES
1. www.socialresearchmethods.net
2. www.statpac.com
3. www.marketresearchworld.com
4. Textbook of Social Research- Ratichhapekar
5. Research Methodologies- C.R.Kothari