a technique in which samples are drawn first from higher order groupings (e.g., states) and then from successively lower level groupings (e.g., counties within states, towns within counties) in order to avoid the necessity of having a sampling frame for the entire population. That is, if subunits within a selected unit give similar results, one can select and measure a sample of the subunits in any chosen unit to avoid uneconomically measuring all of them. When two grouping sets are involved, the process is also known as two-stage sampling, when three sets are involved it is also called three-stage sampling, and so on.