IPHY 2500 Lecture Notes - Lecture 6: Multistage Sampling, Sampling Frame, Simple Random Sample
Document Summary
May result from either poor sampling or poor design for evaluating the variable of interest: volunteer sample where individuals have selected themselves is almost guaranteed to be biased. Ex: taking every 50th name off a student directory. Simple random sample is the simplest, each individual has the same chance of being selected. Cluster sampling is used when our population is naturally divided into groups (which we call clusters), we take a random sample of clusters and use all the individuals within the selected clusters as our sample. Stratified sampling is used when our population is naturally divided into sub-population which we call stratum. We choose a simple random sample from each stratum and our sample consists of all these simple random samples but together. Ex: gender, year in college, registered voters divided by race, high school seniors in a certain city.