Multistage sampling
Definition: The Multistage Sampling is the probability sampling technique where
in the sampling is carried out in several stages such that the sample size gets
reduced at each stage.
A sampling scheme, in which sampling is done in two or more stages
is called multistage sampling.
Multistage sampling divides large populations into stages to make
the sampling process more practical. A combination of stratified
sampling or cluster sampling and simple random sampling is usually
used.
• Example:
• The Census Bureau uses multistage sampling for the National Center for
Health Statistics’ National Health Interview Survey (NHIS). A multistage
probability sample of 42,000 households in 376 probability sampling
units (PSUs are usually counties or groups of counties), which are chosen in
groups of around four adjacent households.
Multistage sampling is used for predicting election result. For example, they
might randomly choose a certain number of area codes then randomly
sample a number of phone numbers from within each area code.
Properties of Multistage sampling
(1) Multistage sampling is a complex form of cluster sampling.
(2) Carried out in many steps.
(3) Information gathered from last stage.
(4) Several chained samples.
Application of Multi-Stage Sampling
and draw procedure with an Example
Multi-stage sampling can be easy to apply in business studies, census bureau etc.
Application of this sampling method can be divided into four stages:
1. Choosing sampling frame, numbering each group with a unique number and selecting a
small sample of relevant discrete groups.
2. Choosing a sampling frame of relevant discrete sub-groups. This should be done from
relevant discrete groups selected in the previous stage.
3. Repeat the second stage above, if necessary.
4. Choosing the members of the sample group from the sub-groups using some variation of
probability sampling.
Let’s illustrate the application of the stages above using a specific example.
A research objective is to evaluate online spending patterns of households in the
Bangladesh through online questionnaires. We can form our sample group
comprising 140 households in the following manner:
1. Choose 14 districts in the using simple random sampling (or any other probability
sampling).
2. Choose 2 tanas within each district using systematic sampling method (or any other
probability sampling).
3. Choose 5 households from each tanas using simple random or systematic sampling
methods. This will result in 140 households to be included in your sample group.
Advantages of Multi-Stage Sampling
1. No complete listing of population is required.
2. Cost-effectiveness and time-effectiveness.
3. High level of flexibility.
Disadvantages of Multi-Stage
Sampling
1. High level of subjectivity.
2. Each stage in sampling introduces sampling error.
3. The presence of group-level information is required.
