e Simple Random sample Highly representative Not possible without random from whole if all subjects complete list of population participate; the ideal population members; potentially uneconomical to achieve; can be disruptive to isolate members from a group; time-scale may be too long, data/sample could change Stratified Random sample Can ensure that More complex, requires random from identifiable specific groups are greater effort than groups (strata), represented, even simple random; strata subgroups, etc. proportionally, in the must be carefully sample(s) (e.g., by defined gender), by selecting individuals from strata list Cluster Random samples Possible to select Clusters in a level must of successive randomly when no be equivalent and some clusters of subjects single list of natural ones are not for (e.g., by population members essential characteristics institution) until exists, but local lists (e.g., geographic: small groups are do; data collected on numbers equal, but chosen as units groups may avoid unemployment rates introduction of differ) confounding by isolating members Stage Combination of Can make up Complex, combines cluster (randomly probability sample by limitations of cluster and selecting clusters) random at stages and stratified random and random or within groups; sampling stratified random possible to select sampling of random sample when individuals population lists are very localized Purposive Hand-pick subjects Ensures balance of Samples are not easily on the basis of group sizes when defensible as being specific multiple groups are to representative of characteristics be selected populations due to potential subjectivity of researcher Quota Select individuals Ensures selection of Not possible to prove as they come to fill adequate numbers of that the sample is a quota by subjects with representative of characteristics appropriate designated population proportional to characteristics populations Snowball Subjects with Possible to include No way of knowing desired traits or members of groups whether the sample is characteristics where no lists or representative of the give names of identifiable clusters population further even exist (e.g., drug appropriate abusers, criminals) subjects Volunteer, Either asking for Inexpensive way of Can be highly accidental, volunteers, or the ensuring sufficient unrepresentative convenien consequence of not numbers of a study ce all those selected finally participating, or a set of subjects who just happen to be available Source: Black, T. R. (1999). Doing quantitative research in the social sciences: An integrated approach to research design, measurement, and statistics. Thousand Oaks, CA: SAGE Publications, Inc. (p. 118)