When subpopulations of the population to be studied vary considerably, it is advantageous to sample each subpopulation (stratum) independently and produce a
weighted mean that has less variability than the
arithmetic mean of a random sample. There are several possible strategies:
- Proportionate allocation uses the same [sampling fraction]? in each of the strata.
- Optimum allocation takes larger samples in the strata with the greatest variability to generate the least possible sampling variance.
- cluster sampling -- [multistage sampling]? -- [simple random sampling]?
back to survey sampling