Skip to main content icon/video/no-internet

After a researcher has decided the research questions or hypotheses to test, he or she must determine how participants for the study will be selected. In most (if not all) cases, it would be cost-prohibitive to study every member of a population, so determining a sample of that population is necessary. A sample is a selected portion of the population to be studied. Several factors require evaluation to determine the appropriate sampling process. Sampling refers to the process of selecting a subset of a population to represent the entire population. Depending on whether the study is quantitative in nature or qualitative (descriptive), the sampling process will vary greatly.

Two sampling processes encompass how samples are selected: probability sampling and nonprobability sampling. This entry discusses those two sampling processes, as well as describes decisions that must be made in relation to theoretical sampling and sample size. The entry concludes by reviewing systematic errors related to sampling.

Probability Sampling

Probability sampling is also known as random sampling. There are different methods for selecting a random sample. A researcher could use a random number generator or select every nth individual within a population. For example, if a researcher wanted a sample within a particular geographical area, he or she could select every 5th, 20th, 50th, etc., (whatever number would provide the appropriate sample size) person from the phone book for that area. Probability sampling is a critical component to quantitative research, in which the sample is expected to be representative of the population. In random sampling, every member of the population has exactly the same chance at being selected to participate in the study.

Stratified Sampling

In some cases, it is not feasible to obtain a random sample from the entire population. In these cases, a stratified random sample might be desirable. A stratified random sample occurs when a researcher decides which sub-groups of a population are to be studied, then randomly selects subjects from each sub-group. An example might be particular ethnicities. If a researcher would like to gather data from African Americans, Irish Americans, and German Americans for a study, after determining how many participants from each group is necessary, participants representing those sub-groups could be selected.

Cluster Sampling

Another random sampling technique is called cluster sampling. Cluster sampling relies on geography to determine the sub-group to be sampled. For example, a researcher may desire to study a particular metropolitan area. The population for this metropolitan area might be divided by neighborhoods or school districts and then each of those clusters will be separately sampled.

Nonprobability Sampling

Nonprobability sampling is when samples are not selected based on random selection. Instead, particular samples may be chosen because of certain qualities or based on the availability or representation of a sub-population of interest. Two types of nonprobability sampling are purposive and convenience sampling.

Purposive Sampling

Purposive sampling refers to sampling in which the participants are selected who are believed to have the most relevant knowledge or information for the study. In this case, the sample is specifically selected intentionally to gather the data necessary for the study.

...

  • Loading...
locked icon

Sign in to access this content

Get a 30 day FREE TRIAL

  • Watch videos from a variety of sources bringing classroom topics to life
  • Read modern, diverse business cases
  • Explore hundreds of books and reference titles

Sage Recommends

We found other relevant content for you on other Sage platforms.

Loading