Multistage sample

Multistage sampling is what large national surveys do when no list of every individual exists. For example, you might randomly select 30 school districts, then randomly select 4 schools within each chosen district, then randomly select 25 students within each chosen school. Every stage uses a random mechanism, and the stages often mix methods, such as cluster sampling followed by a simple random sample inside each cluster. The AP course names four random sampling methods (simple random, stratified, cluster, and systematic), so describe a multistage design stage by stage rather than with one label.