PS295 Chapter Notes - Chapter 5: Stratified Sampling, Simple Random Sample, Cluster Sampling
Systematic Sampling:
-involves taking every so many individuals for the sample
-ex chosing every 4th person
-not simple random bc after we select a particular participant, the next several people
have no chance at all of being in the sample
Stratified Random Sampling:
-a variation of simple random sampling
-divide population into 2 or more subgrouns or strata
Stratum:
-a subset of the population that shares a particular characteristic
-ex divide into men vs women
-different racial groups
-age ranges etc
-then cases are randomly sampled from each of the strata
-ensures researchers have adequate numbers of participants from each stratum
Proportionate sampling method:
-cases are sampled from each stratum in proportion to their prevalence in the population
Document Summary
Involves taking every so many individuals for the sample. Not simple random bc after we select a particular participant, the next several people have no chance at all of being in the sample. Divide population into 2 or more subgrouns or strata. A subset of the population that shares a particular characteristic. Then cases are randomly sampled from each of the strata. Ensures researchers have adequate numbers of participants from each stratum. Cases are sampled from each stratum in proportion to their prevalence in the population. Drawback of this and stratified sampling is that they require we have a sampling frame of all cases in population before we begin. Researcher first samples groupings or clusters of participants. Clusters often based on naturally occuring groupings like geographical areas or institutios. Randomly sampling large clusters, then sampling small clusters from within the larger ones, then even smaller ones to obtain sample. Sampling frame of population not needed to begin sampling.
