Survey Design

Samples from the sample

The multilevel sample

The multistage sample is a random selection procedure in which the samples of the survey units to be considered are drawn in two or more selection stages.

For this purpose, a sample is drawn from the population, mostly from a higher hierarchical level. Then another sample is drawn from this sample. A multi-level selection makes sense if the population is hierarchically structured, for example at the levels between the federal government and federal states or federal states, districts and municipalities.

In practice, infas often uses a combination of lump sample, stratified sample, and ADM sample. For example, a Resident Registration Office sample is a two-stage, clustered, stratified sample. In the first stage, communities are randomly selected according to the Probability Proportional to Size (PPS) process, with the number of community targets being MOS = Measure of Size and sample points selected. In the second stage, the same number of persons is randomly selected (usually via systematic random selection) within the selected sample points. The selection of the municipalities or sample points on the first level is usually stratified according to regional and regional structural characteristics.