Convenience sampling is one of the most commonly used sampling methods in behavioral intervention research. Convenience samples are based on individuals who are available, are interested in participating in a study, and, of course, who meet study inclusion/exclusion criteria. These samples are often obtained through access to a particular group (e.g., students in a class), advertisement, community outreach activities (e.g., speaking at a support group), clinical lists, or participant registries. As is common in behavioral intervention research, in the PRISM study (Czaja et al., 2014) it was not possible to randomly select 300 persons aged 65+ who lived alone and who were “at risk” for social isolation from a list of the total population of individuals meeting this criteria. Instead, a variety of recruitment activities (e.g., radio and newspaper advertisements, outreach to community agencies serving these populations) were employed at each of three participating sites to identify, recruit, and enroll study participants who were representative of the population the intervention was intended for on relevant characteristics.
Clearly, convenience samples have limitations, particularly with concerns about generalizing to the population level. Thus, they limit the ability of intervention studies to fully examine the external validity of the findings of the study since every member of the population does not have a chance of being included in the sample and thus the sample does not truly represent the population at large. However, the external validity of convenience samples can be increased by ensuring that the sample is as representative of the target population as possible and by minimizing sample bias as much as possible.