Sampling Techniques

Random sampling
This is also referred to as probability sampling. In this method, each item of the
population under consideration has an equal chance of being selected as part of the
sample. Each item in the population is selected independent of the rest of the items.

Random sampling is further broken down into simple random sampling and
stratified sampling.

Simple random sampling

This method uses a sampling frame that lists all members of the target population
giving each member an equal chance of being selected in the sample.

Advantages of simple random sampling

The sample is generated with ease.

It eliminates bias because every member of the population has an equal chance
of being considered.
The sample is always representative of the population.
Disadvantages of simple random sampling

Time consuming, since the entire population is involved.

There is a tendency to down play or over emphasize certain significant attribute
of the population.
Quite costly when the population covers a wide geographical area.
Stratified sampling

This involves obtaining simple samples from each of the strata of the population and
the simple samples combined to give the stratified sample of the population.

Advantages of stratified sampling

It eliminates bias.
Ensures a better coverage of the population.
Easy to apply and achieves better precision than the simple random sampling.
Disadvantages

It requires an extensive sampling frame.

Strata of importance may be selected subjectively.
Time consuming.
Quite costly.
Quasi random sampling
 This is appropriate when random sampling is not possible and too expensive to carry
out.

Systematic sampling

This method is used when the population is listed in a given order or some of it is
physically in evidence. For example, a row of houses or clients visiting a particular
webpage in one hour on a given day.

Advantages of systematic sampling

It is easy to implement.
Works where there is no sampling frame as long as the items are physically in
evidence.
Saves time and is not costly.
Disadvantages of systematic sampling

Bias may occur where recurring sets in a population are possible.

This sampling technique is not perfectly random. Once the starting point has
been determined, all the subjects are predetermined, hence the same quasi
random sampling.
Multi-stage sampling

This method is most suitable when the population is spread over a relatively
wide geographical location.

Advantages of multi-stage sampling

Takes less time to accomplish.

Requires a small man power to execute.
Less costly compared to random sampling.
Disadvantages of multi-stage sampling

It is subject to bias, especially when a few regions are selected.

It is not truly random. At each sampling stage, the population left out has no
chance of ever making it to the final sample.
Non-random sampling

This is a method used when the random sampling techniques are impossible or not
practical to use. This method comprises of cluster and quota sampling techniques.

Cluster sampling
 This method is implemented by selecting one or more geographical areas,
sampling all the members of the target population that can be identified.

Advantages of cluster sampling

It is a good alternative to multi-stage sampling.

Little organization or structure needed in the selection of the subjects.
It is cheap to carry out.
Disadvantages

Being non-random may lead to selection bias.

Quota sampling

This method employs a team of interviewers; each assigned a set number of subjects
referred to as the quota to the interviewer. The population is usually stratified in some
way and this helps the quota. A lot of responsibility is placed on the interviewers
because selection of subjects is left to them entirely.

Advantages of quota sampling

The population is usually stratified.

It has no non-responses errors.
Less costly and convenient.
Disadvantages of quota sampling

Sampling is non-random and may, therefore, lead to selection bias.

Quite challenging to implement and may lead to interview bias.