Difference between stratified and cluster sampling?

Basically in a stratified sampling procedure, the population is first partitioned into disjoint classes (the strata) which together are exhaustive. Thus each population element should be within one and only one stratum. Then a simple random sampling technique is applied and samples are taken out from each stratum for the final sample. This can be of two types:

  1. Disproportional: while selecting the samples from each stratum, we select equal no of samples.
  2. Uniform/proportional: Selecting the samples in a proportion similar to that of each strata.

Cluster sampling is two stage simple random sampling. We break the population into many groups (called clusters). Then we sample some no of clusters for study purpose.

Both techniques are similar with only one difference is that in stratified, we need to take samples from each strata while in cluster we can take some cluster and start with our analysis.

Leave a Reply

Your email address will not be published. Required fields are marked *