Page 66 - SREENARAYANAGURU OPEN UNIVERSITY

sampling. Under area sampling we first divide the total area into
a number of smaller non-overlapping areas, generally called
geographical clusters, then a number of these smaller areas are
randomly selected, and all units in these small areas are included in
the sample. Area sampling is helpful where we do not have the list
of the population concerned. It also makes the field interviewing
◆ Based on more efficient since interviewer can do many interviews at each
geographical areas location. In a study where we are trying to find out socio-economic
status in a Taluk, then we need to take the map of the Taluk and
lay out a grid with lines of equal intervals. Say if we get 50
equal squares that mean we have 50 areas. We can exclude non-
residential areas in the area. Put sequential numbers to all other
squares. Make a house count in each area, say 40 households and
the total sample required is 320. In this case, we need to study 8
squares (area) {320/40=8}. If we study all the households in these
8 areas we can attain the required sample.
E. Multi stage sampling
Where sampling is carried out in multiple numbers of stages it

◆ Multiple stages is called multi-stage sampling. In order to draw the final sample,
a researcher does a stage-by-stage selection and finally arrives at
the required number of respondents. This is a further development
of the idea of cluster sampling. This technique is meant for big
inquiries extending to a considerably large geographical area like
an entire country.
For example, in a study of employees in the service sector in
Kerala, the researcher in the first stage may select the service
sector which he intends to study, say banks and insurance. At
the next stage, the kind of institutes are identified, say National,
State or local banks and then at the third stage, the respondents are
selected from the institutions identified at the second stage. This
method helps in identifying samples very systematically covering
the entire population. It saves time, money and labour as it can
concentrate on small areas.
2.1.4.2 Non- Random Sampling or Non-Probability Sampling
◆ Unequal chance for When probability sampling ensures equal chance for each
selection element to be selected, non-probability sampling doesn’t offer
equal chance of selection to each element in the population. There
are various methods adopted under this technique discussed as
under.
A. Purposive or judgement sampling
Under this method the researcher fixes a predetermined criteria
and selects a sample which matches the said criteria alone as
sample. The selection of the sample depends on the judgement
of the researcher. For example, a teacher may select only those
who he/she thinks would be aspiring for CA in order to conduct

60 SGOU - SLM -MCom Research Methodology