SAMPLING
Aim of sampling reflects a accurate
characteristic of population.
CENSUS VS SAMPLE
SURVEY:
The required information in any
scientific enquiry may be collected by
following either census method or
sampling method.
• All items in any field of inquiry constitute a universe
or population.
• Under the census or complete enumeration method
information is collected from each and every
element of the population.
• But many a time it is not possible to examine every
item in the population and a researcher relies on
studying only a part of the universe which can also
provide accurate results.
• Under sampling method information is collected
from only a part of the population called a sample.
And on the basis of the information conclusions
are drawn for the whole population.
• The selected respondents constitute-a sample
• The selection process is called-sampling
technique.
• The service so conducted is-sample survey
N-POPULATION
n-Sample
Researcher must prepare a sample design for his
study. That is he must plan-
• How a sample should be selected
• What size of sample is to be selected
• Sample design is determined before the data are
collected.
STEPS IN SAMPLE DESIGN:
[Link] of universe: First a universe is
selected. It can be finite or infinite .In
finite universe the number of items is
certain ,but incase of an infinite
universe the number of items is
infinite.
[Link] Unit :A sampling unit is to be
chosen. It may be a geographical area,
state ,city etc or a social unit like
family ,school, etc or it may be an
individual
[Link] list: It contains the names of all
items of a universe. It should be correct
or reliable.
[Link] Of Sample: This refers to the
number of items to be selected from the
universe to constitute a sample. It
should not be too large or too small.
5. Sampling Procedure: He must decide
about the technique to be used in
selecting the items for the sample.
Infact this procedure or technique is
nothing but sample design. A researcher
must select that design ,which minimize
cost and has small sampling error.
SAMPLING METHODS
NON-PROBABILITY PROBABILITY
SAMPLING SAMPLING
Non-probability Sampling
• [Link] sampling
• [Link] /judgment sampling
• [Link] sampling
• Non probability sampling:
It is that sampling procedure which doesn’t
have any rules or procedures of estimation of
sample. Here ,items for sample are selected
deliberately by the researcher.
Convenience Sampling: In this method
the researcher selects those units of
population which appear convenient to
him. Ex-interviewing people whom we
happen to meet. Here those units are
included in the sample which are
conveniently available.
• Purposive Sampling: It is also called
the judgment sample. Here the sample is
selected by choice ,not by chance. It is
based on the judgment of the researcher.
Here the selection of items are made are
made according to the subjective
judgment of the researcher.
• Quota Sampling: It is a method often
employed in market research and public
opinion polls,in which the interviewers
receive the quota or number of persons to
be interviewers receive the quota or
number of persons to be interviewed
based on income age etc
Probability sampling
• [Link] random sampling
a. lottery method
b. table of random numbers
[Link] sampling
[Link] random sampling
[Link] sampling
[Link] sampling
Probability Sampling
• Probability sampling is also known as random
sampling or chance sampling. Under this
sampling design, every item of the universe
has an equal chance of inclusion in the sample.
• Simple Random Sampling: Simple
random sampling implies that every item of the
population has an equal chance of being
selected in the sample .Here sampling is done
without replacement. A simple random
sampling can be selected by lottery method or
table of random numbers
• Lottery Method: Simplest Method. Here ,We
Write Each Of The Possible Samples On A Slip Of
Papers ,Mix These Slips In A Container And Then
Draw As a lottery one after the other ,till the
required no. of sample is drawn .this method is
useful for drawing a small sample from a small
population
• Table Of Random Numbers: generally
tippet's random number tables are used for this
purpose. this is a less cumbersome, but equally
valid procedure of sample selection. to select a
random selection out of a given frame ,one
should simply start to need numbers from table
of random number at any randomly selected point
and pick-out numbers within the range of the
frame
Systematic sampling
• In some cases , the most practical way of
sampling is to select every ith item in the
list . it is systematic sampling .here
element of randomness is there . suppose
it is desired to select 20 students out of
300 hundred . then divide 300 by 20
which is 15.
• Stratified random sampling-
if population is not homogeneous stratified
random sampling can be used . in this
method the population is subdivided into
homogeneous groups or strata and from
each strata random sample is drawn.
Ex-customer can be classified according to
their financial status , and then draw
samples from each class.
• Cluster sampling:
where the population is scattered over a
wide area , then a convenient way in
which a sample can be taken is to divide
the area into a number of smaller areas
(clusters) and then select some of the
clusters randomly and from these
clusters take samples using random
sampling.
• Multistage sampling:
It is a further improvement of cluster
sampling .here sample is taken in each
stages. first ,a sample of first stage
sampling unit is drawn , then from the
each of the selected first stage sampling
unit a sampling unit is drawn . and it may,
continue appropriate random sampling
method is adopted at every stage.
Parameter and Statistics
• Parameter is a measure of characteristics
of an entire population based on all the
elements within that population.
• Statistics is a measure of characteristics
about the sample under study.