PO217 Lecture 5: Po217 lecture 5
Document Summary
Po217 lecture 5 the same accuracy at a lower cost. Increases the level of accuracy for a given total sample size or achieves. It may not be possible to stratify on theoretically crucial variables because we don"t know their values ahead of time (income, education) Disproportionate stratified random samples strata and or under sample"s others. Done for analytical reasons: 1. categories of iv 2. Same as proportionate except that the research deliberately over-samples some. Facilitate statistical analysis by having an equal number of cases in the different. To ensure sufficient cases for meaningful analysis where stratum is small but substantively or theoretically important. Cluster sampling eeds in stages then randomly selecting clusters within which to randomly sample elig. Used when no population list is available (e. g. all university students in canada, all ible voters, all catholics). Process of dividing the population into a number of subgroups known as clusters and.