This document discusses stratified sampling, which involves dividing a population into subgroups or strata based on characteristics. Samples are then randomly selected from each stratum.
Some key points:
- Stratification allows for greater precision than simple random sampling of the same size. It can reduce variation within strata.
- Common variables to stratify on include demographics, locations, weights.
- Advantages include greater precision, smaller sample sizes, and ability to focus on important subgroups. Disadvantages include more work and difficulty selecting variables.
- The size of each stratum sample is usually proportional to the stratum's size in the overall population. This is called proportional allocation.