Sampling

 Sampling refers to selecting a subset of the entire

population for the purpose of research study.
 Census refers to the complete enumeration of all
elements in a population or universe whereas sample
survey refers to the study of some selected elements from
the population.
 Census versus Sample
Census
Survey Sample Survey

Used when population Used when population

contains less elements and contains numerous
it is feasible to study each elements and it is not
element therein feasible to study each
element therein

Used when there is no cost Used when there is cost

constraint constraint

Used when the researcher Used when the researcher

has enough time and does not have enough time
resources to conduct and resources to conduct
complete enumeration complete enumeration
 Steps involved in developing
sampling design
a) Type of population: population can be finite or infinite
b) Sampling frame : refers to the list of all the elements in a
population
Types:
Incomplete frame: refers to the frame in which genuine sampling
units of population are absent.
Inaccurate frame : refers to a frame in which some of the
elements are mentioned in an incorrect form.
Inadequate frame : refers to a frame that does not include a list of
all elements in a population
c) Sampling unit: Refers to division of a population
d) Sampling method: Refers to the methods by which
sampling units are selected.
e) Sampling size: Refers to number of items in a sample.
f) Parameters: Refers to the factors that are interest to the
researcher in obtaining a sample from the population.
g) Budgetary constraints: Refers to cost-related
constraints.
 Sampling Errors
 Also known as random errors, refers
to the errors that occurs due to
observing only a sample from the
whole population.
 Methods to reduce sampling
errors:
 Increasing sample size
 Stratification
Non-sampling errors
 Non-sampling errors are the errors
that do not occur because of
sampling.
Reasons:
 Improper division of sampling units
of a population
 Poor response of respondents
 Bias
 Characteristics of a good
sampling design
 Sampling design must produce representative sample
 Sampling design must result in less sampling errors
 Sampling design must be feasible in context to available funds
 Sample design should result in such type of sample whose result can be
applied to whole population
 Sampling design should be able to prevent bias in a better way.
 Sampling Techniques
A)Probability Sampling Techniques
B)Non-Probability Sampling
Techniques
 Probability Sampling

 Probability sampling is defined as a sampling technique

in which the researcher chooses samples from a larger
population using a method based on the theory of
probability.
 For a participant to be considered as a probability
sample, he/she must be selected using a random
selection.
 The most critical requirement of probability sampling is
that everyone in your population has a known and
equal chance of getting selected.
Different types of probability
sampling-
a)Simple random sampling
b)Systematic sampling
c)Stratified sampling
d)Cluster sampling
e)Multistage sampling
 a) Simple random sampling

 Simple random sampling is an entirely random method of

selecting the sample. This sampling method is as easy as
assigning numbers to the individuals (sample) and then
randomly choosing from those numbers through an
automated process. Finally, the numbers that are chosen
are the members that are included in the sample.
 There are two ways in which researchers choose the
samples in this method of sampling: The lottery system and
using number generating software/ random number table.
Advantages and Disadvantages of a Simple
Random Sample

Random sampling offers two primary advantages.

 Lack of Bias
 Simplicity
Disadvantages of a Simple Random Sample
 Difficulty Accessing Lists of the Full Population
 Time Consuming
 Costs
 Sample Selection Bias
 b)Systematic sampling
 It is the type of probability sampling, in which one or
two items are selected randomly, but other items are
selected by adding the average sampling interval to
the item selected randomly.
 It is also called an Nth name selection technique.
 Selecting every nth subject from a list of the member
of the population.
 Advantages and Disadvantages of a Systematic
sampling

The pros of systematic sampling include:

 Easy to Execute and Understand

 Control and Sense of Process

 Clustered Selection Eliminated

There are also drawbacks to this research method:

 Assumes Size of Population Can Be Determined

 Need for Natural Degree of Randomness

 Greater Risk of Data Manipulation

c) Stratified sampling

 Stratified random sampling involves a

method where the researcher divides a
more extensive population into smaller
groups that usually don’t overlap but
represent the entire population.
 Advantages and Disadvantages

 Advantages:
 Stratified Random Sampling provides better precision as it
takes the samples proportional to the random population.
 Stratified Random Sampling helps minimizing the biasness
in selecting the samples.
 Stratified Random Sampling ensures that no any section of
the population are underrepresented or overrepresented.
 As this method provides greater precision, greater level of
accuracy can be achieved even by using small size of
samples. Disadvantages:
 Stratified Random Sampling requires more administrative
works as compared with Simple Random Sampling.
 It is sometimes hard to classify each kind of population into
clearly distinguished classes.
 Stratified Random Sampling can be tedious and time
consuming job to those who are not keen towards handling
such data.
 d) Cluster sampling

 Cluster sampling is a sampling

method in which the entire
population of the study is divided
into externally homogeneous, but
internally heterogeneous, groups
called clusters. Essentially, each
cluster is a mini-representation of
the entire population.
 Advantages and
Disadvantages
Advantages of Cluster Sampling

 1. Requires fewer resources

 2. More feasible

Disadvantages of Cluster Sampling

 1. Biased samples

 2. High sampling error

 e)Multi-Stage Sampling

 Multi-stage sampling involves a

combination of two or more of the
probability sampling methods outlined
above.
 With more advanced research, using just
one form of probability sampling does
not ensure the randomization necessary
to ensure confidence in results.
NON-PROBABILITY SAMPLING

Non probability sampling refers to

the type of sampling in which
elements from the population are
selected deliberately by the
researcher to constitute a sample.
Types
 CONVENIENCE SAMPLING
 JUDGMENTAL SAMPLING/
PURPOSIVE
 SNOWBALL SAMPLING
 QUOTA SAMPLING
CONVENIENCE SAM-
Sometimes known as grab or opportu-
PLING
nity
sampling or accidental or haphazard
sampling.
A type of non probability sampling
which
involves the sample being drawn from
that part of the population which is
close to hand. That is,
readily available and convenient.
Advantages
• Simplicity of sampling and the ease of research
• Helpful for pilot studies and for hypothesis generation
• Data collection can be facilitated in short duration of
time
• Cheapest to implement
Disadvantages
• Highly vulnerable to selection bias
• High level of sampling error
• Studies that use convenience sampling have little
credibility due to reasons above
 JUDGMENTAL SAMPLING/
PURPOSIVE
 The researcher chooses the sam-
ple
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
Judgmental Sampling Advantages
1. Consumes minimum time for execution
2. Allows researchers to approach their target
market directly
3. Almost real-time results
Limitations:
1. Highly subjective
2. Generalization is not appropriate.
3. Certain members of the population will have a
smaller chance or no chance of selection compared to
others.
4. This method does not give representative part of
the population, since favoritism is involved.
 SNOWBALL SAMPLING

 Selection of additional respondents is

based on referrals from the initial re-
spondents.
Used to sample from low incidence or
rare
populations.
Advantages of Snowball Sampling
• The chain referral process allows the researcher to
reach populations that are difficult to sample when
using other sampling methods.
• This sampling technique needs little planning and
fewer workforce compared to other sampling
techniques.
Disadvantages of Snowball Sampling
The researcher has little control over the sampling
method. Representativeness of the sample is not
guaranteed.
Sampling bias is also a fear of researchers when using
this sampling technique.
 QUOTA SAM-
PLING
In quota sampling, a population is first segmented into
mutually exclusive sub-groups, just as in stratified sam-
pling.

Then judgment is used to select the subjects or units

from each segment based on a specified proportion.
The Advantages of Quota Sampling
• Relatively easy to administer
• Can be performed quickly
• Cost-effective
• A useful method when probability sampling
techniques are not possible
Disadvantages of Quota Sampling
• Sample selection is not random
• There is a potential for selection bias, which can
result in a sample that is unrepresentative of the
population
 V. Data Collection
Data can be defined as a systematic
record of a particular quantity.
 Types of Data

• Quantitative Data and Qualitative Data

• Primary and Secondary Data
Quantitative Data and Qualitative Data

• Qualitative data is defined as the data that

approximates and characterizes. They depict
descriptions that may be observed but cannot be
computed or calculated.
• Quantitative Data: These can be measured and not
simply observed. They can be numerically
represented and calculations can be performed on
them.
 Primary Data
These are the data that are collected for the first
time by an investigator for a specific purpose.
Primary data are ‘pure’ in the sense that no
statistical operations have been performed on
them and they are original.
Merits Demerits
1. It has high degree of 1. It requires lot of
accuracy. time.
2. For some enquiries, 2. It needs much
secondary data is not money.
available. 3. These data can be
3. These are more obtained though skilled
reliable. persons only.
4. Sometimes, these
data are not available
altogether.
 Secondary data:
These are the data which are collected from
some secondary source i.e. the source of
reservation storage where the data is
collected by one person and used by other
agency. These are collected
Merits as primary data
Demerits
and
1. It used byto
is easy other as secondary
collect. data.
1. These are not reliable
2. Time and money is as primary data.
saved. 2. Extra caution is
3. Sometimes primary needed to use these data.
data cannot be obtained. 3. All types of data are
4. Some data are more not available.
reliable than primary. 4. Purpose of original
collection may have been
different.
 SOURCES OF
SECONDARY DATA
(i) Govt. Publications:
Ministries and Department of various ministries of India and
states publish the data relating to their departments or
ministries.
(ii) Semi-government Publications:
These are the institutions such as Municipal Councils and Zila
Parishads. These publish data about births and Deaths, Health
and Education etc.
(iii)International Publications:
World bodies such as I.M.F., World Bank, W.T.O.; W.H.O etc. also
publish the data regarding their organisations.
(iv) Reports of Committees and Commissions:
Union and state governments at time appoint some
committees or commissions to make research into any problem
such as Finance Commission, Minority Commission, Planning
Commission etc.
(v) Publication by Trade Business Association:
Big trade and business associations also publish
periodic data about trade and industry which are of
much use. These data is used by scholars to analyse
various problems being faced by the country.
(vi) Newspapers, Magazines and journals:
These are one of the main providers of data on day to
day basis.
(vii) Private Publications:
Some private institutions belonging to big education
houses also bring out their publications with data on
different topics.
(viii) Research Institutes and scholars:
Indian Statistical Institute, C.S.O and N.S.S.O etc. also
publish the data available with them.
(ix) Libraries and Internet
METHODS OF PRIMARY DATA
COLLECTION
Observation method
Interview method
Questionnaire method
Schedule method
OBSERVATION METHOD
Observation method is a method in which the population of
interest is observed to find out relevant facts and figure.
Sub-methods of observation method
Natural method
Contrived method
Direct method
Indirect method
Structured method
Unstructured method
Mechanical method
 INTERVIEW METHOD
In this method, a researcher asks the respondents to
react or speak on a particular topic or situation.
Types of interview method
Structured Interview
Unstructured Interview
Individual in depth interviews
Group Interviews
Telephonic Interviews
Computer-assisted Interviews
 QUESTIONNAIRE METHOD
Questionnaire is a research instrument that
consists of a set of questions that aims to collect
information from a respondents.
Phases of designing a questionnaire
Defining objectives of the questionnaire
Deciding the types of questions
Writing questionnaire
Evaluating questionnaire
 WRITING QUESTIONNAIRE
It asks for and obtains all the information required for
achieving the research objectives.
It contains questions relevant to the study and does not
include any irrelevant and unimportant questions.
It does not aim at obtaining any information which can
be more accurately and effectively obtained by other
data gathering methods like observation.
It contains no questions that are un clear, ambiguous
and long.
It contains no open-ended or discussion questions unless
they are absolutely necessary.
It does not contain questions which are beyond the
memory span of the respondents.
It contains questions that can be answered as quickly
and easily as possible.
Choices to closed questions are adequate, reasonable,
and logically consistent.
Each question is limited to a single idea or single
reference.
No embarrassing questions are given without providing an
opportunity to explain.
Topics and questions are arranged in a logical and
sequence that is natural and easy for the respondent.
Questions and alternative answer choices are properly
coded.
Design requirements like margin, spacing etc., are taken
care of.
Appropriate introduction and instructions are included.
The instrument has been adequately pre-tested and revised
so as to be a satisfactory tool for the particular survey.
SCHEDULE METHOD

In schedule method enumerators are appointed to

conduct the research. These enumerators meet the
respondents personally and fill the questionnaire
themselves.