ABSTRACT
This chapter discusses simple random, stratified random, and random cluster sampling and the use of a table of random numbers. It shows that while there are sampling methods to minimize sampling error, random sampling is not without sampling error. A population may be small, such as all social workers employed by a public hospital in Detroit, or it may be large, such as all social workers in Michigan. An unbiased sample is defined as one in which all individuals in a population have an equal chance of being included as a participant. To draw a simple random sample, a researcher can put names on slips of paper and draw the number needed for the sample. Stratified random sample being considered, the benefits of randomization have been retained. For large-scale studies, multistage random sampling may be used. Unlike simple random sampling, in which individuals are drawn, in cluster sampling, clusters are drawn.
