Sampling and Data Collection

Sampling: Census is a method of study in which all the items of
population or universe are counted and studied. Census requires more

money, manpower, and time. There are many instances where it is not
practicable to enumerate all the units due to their perishable nature.
When only a part of the population is selected for the study then it is
called sample survey. A sample survey will usually be less expensive
and desired information will be obtained in less time by maintaining
desired degree of accuracy.
Sample survey have following advantages over census survey:
a) Greater scope b) Shorter time lag c) Greater economy
d) Higher quality of work
Sampling is appropriate when: universe is very large, universe possess
homogeneous characteristics, utmost accuracy is not required,
census is impossible (in case of destructive nature of units)
Census is appropriate when: universe is small, population is
heterogeneous, hundred percent accuracy is required.
Sampling process
1. Define the population: In first step population of the study should
be defined. Wrong definition of population will lead meaningless
and misleading findings. A populating must be defined in terms is
elements (price of competing brand), sampling units (department
stores), extent (Kathmandu Valley), and time (from-----to----).
2. Specifying the sampling frame: A sampling frame is a means
which represents the elements of the population. A sampling
frame may be a telephone directory, trade directory, voter list,
employee roster etc,. A perfect sampling frame includes every
element of the population is represented once and only once.
3. Specifying the sampling unit: Sampling unit is the basic unit
which contains the elements of the population to be sampled. For
a family budget survey, sampling unit is household and for
telephone survey, sampling unit is telephone number. Sampling
unit should be further specified that who should be interviewed in
house hole or telephone.
4. Selection of the sampling method: Sampling method is the technique
by following which samples are drawn from the population. In this
step an appropriate method is selected from available methods.
5. Determination of the sample size: It is very important aspect in
sampling because degree of accuracy depends upon size of sample.
Decision of size of sample is based on cost and degree of desired
accuracy.
6. Specification of the sampling plan: The sampling plan involves the
specification of decisions on each of the five steps discussed above.
This steps provides the operational definition of the sampling unit,
starting and ending points, contact procedures, callback procedure,
and other contingencies during interview period.
7. Implication in the field situation: The last step is to implement the
sampling in the field situation. This requires hiring and training
interviewers and assigning duties and responsibilities to field officers,
supervisors and interviewers.
Methods of sampling
Methods of sampling can be divided into two broad categories:
1. Probability sampling: in this method, every element in the
population has a known non-zero probability of being selected as
a sample. This probability is attained through some mechanical
operation of randomization. There are five major methods which
can be used for this purpose:
a) Simple random sampling b)Stratified random sampling
c) Cluster sampling d) Systematic sampling e) Multistage sampling.
2. Nonprobability sampling: in this method samples are not
determined by the chance, but rather by personal judgment or
convenience of the researcher. There are four methods used for
this purpose:
a) Convenience b) Quota c) Judgment d) Snowball
1. Simple random sampling: this is common method of sampling in
which samples are drawn from the population in such a way that
all the items of the population have equal probability of being
selected in the sample. If population is homogeneous and entire
list of population can be listed this method can be used. Table of
random number or lottery method can be used to draw the
sample.
2. Systematic sampling: in this method first sample is randomly
selected and remaining samples are selected at every nth
intervals and ‘n’ is fixed by dividing population size by sample
size.
3. Stratified sampling: when population is heterogeneous and we
want to represent each group in the sample this method can be
used. In this method population is divided into different
homogeneous groups called strata, then simple random sampling
procedure is used to draw sample from each stratum. Samples
may be drawn proportionately or nonproportionately from each
stratum.
4. Cluster sampling: in this method population is divided into different
groups called clusters in such a way that items within the cluster is
heterogeneous and between the cluster is homogeneous. For
example population of a municipality is divided into different wards
and simple random sampling is used to draw samples from each
cluster.
5. Multi-stage sampling: in this method required size of sample is
obtained by sampling in different stages. For example to survey the
yield of a crop in a district, at first stage VDC is selected, in second
stage village is selected, and field is selected in third stage.
1. Convenience sampling: In this method selection of sample is totally
based the convenience of the researcher. When time and money
are seriously limited, this method is widely used.
2. Judgment sampling in this method samples are drawn through
researcher’s intuition or some other subjective basis. The sample
representativeness is highly dependent upon the good judgment of
the researcher.
3. Quota sampling: This method is used to represent different groups
of the population in the sample. in this method population is
broken down on the bases of key demographic characteristics and
samples are drawn.
4. Snowball Sampling: this method is used where respondents are
difficult to identify. Individuals are discovered and are selected for
study. This group is then used to locate others who possess similar
characteristics and who, in turn, identify others.

Sampling and Data Collection

Uploaded by

Copyright:

Available Formats

Sampling and Data Collection

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Sampling and Data Collection

Uploaded by

Copyright:

Available Formats

Sampling: Census is a method of study in which all the items of

population or universe are counted and studied. Census requires more

You might also like