Identities and intersectionality: A case for purposive sampling in survey-experimental research

This chapter begins by reviewing the strengths and weaknesses of various approaches for obtaining samples of intersectional identity groups, and then provides some empirical evidence for the viability of general population samples for providing large numbers of respondents from intersectional identity groups. Purposive sampling can be thought of as a subset of convenience sampling, in that respondents are chosen subjectively. While convenience sampling necessarily relies upon untestable assumptions rather than probability-based sampling methods, the chapter argues that such methods may be more appropriate for survey-experimental research than for observational research. For the purposes of experimental research on small intersectional identity groups, many purposive samples may be fit for use because they trade off design-based representativeness against obtaining a sample size sufficiently large to powerfully estimate an experimental effect size.