Sampling Sizes: How Much Is Enough

Sampling Size: Qualitative Research

The aim of qualitative research is to ensure that the population in question is studied with sufficient rigor and above all sufficient depth to yield meaningful results. "There is a point of diminishing return to a qualitative sample -- as the study goes on more data does not necessarily lead to more information… qualitative research is concerned with meaning and not making generalised hypothesis statements" (Mason 2010:8). The advantage to large sampling sizes is that they are more representative as a whole and are less likely to be thrown off by anomalies: "for qualitative studies, where the goal is to 'reduce the chances of discovery failure,' a large sample size broadens the range of possible data and forms a better picture for analysis" ("The importance of a quality sample size," 2013, Unite for Sight). In the process of qualitative research, when a small sampling size is selected even though "these informants are purposefully selected and the data themselves seem valid, there is no guarantee that these informants' views are typical" (Maxwell 2005: 91). However, the ultimate purpose of qualitative research is to give attention to anomalies and to devote intense attention to a specific case study in great depth. This makes using very large numbers logistically unfeasible, given that the amount of quality time which can be spent with individual patients will inevitably be diluted (Maxwell 2005: 91-92)

Quantitative research is numerical and data-driven, and thus there are specific, statistical standards which must be met in terms of determining sample size. In contrast, determining an appropriate sample for qualitative research is primarily dependent upon finding a 'saturation point' for the data (Mason 2010:8). In other words, how many people do you need to collect data upon until no additional meaningful information will be yielded? To avoid diluting the quality of the in-depth, concentrated research, understanding the saturation point is critical. "Saturation determines the majority of qualitative sample size" (Mason 2010:8). However, saturation is very difficult to establish and can be somewhat subjective. "Researchers often claim to have achieved saturation but are not necessarily able to prove it" (Mason 2010:8).

For example, in the case of my area of study of human trafficking, to gain a representative sample I might find it necessary to talk to women of a variety of nationalities; backgrounds; ages; reasons for being trafficked; and past personal history (given that previous emotional trauma can influence their perceptions of being trafficked). If I was comparing the experiences of men and women being trafficked I would also have to speak to males of similarly diverse backgrounds. It would take a long time to reach a 'saturation point' given such diversity. However, if I was only focusing on the female gender, a specific nationality, or specific reasons the persons in question had been trafficked, my saturation point would be much lower and thus my sample size would be much smaller. The intention of my research -- whether I wanted to create a prescriptive, grounded theory about how to deal with trafficked persons or if the research was just exploratory -- would also determine the sampling size, given that creating a theory requires a larger and more comprehensive, representative sampling in general (and thus would demand more labor).