Ask eAIR invites questions from AIR members about the work of institutional research, careers in the field, and other broad topics that resonate with a large cross-section of readers. If you are interested in writing an eAIR article, or have an interesting topic, please contact eAIR@airweb.org.
This month’s question is answered by Steve Graunke, Director of Institutional Research and Assessment, IUPUI.
The ideas, opinions, and perspectives expressed are those of the authors, and not necessarily of AIR.
Dear Steve: My institution is starting to put a lot more emphasis on qualitative sampling when it comes to collecting data for decision making. Can you provide any guidance on qualitative sampling strategies and the reason for using each type?
The first thing to remember when considering qualitative sampling procedures is that the goals of qualitative studies are inherently different than quantitative studies. While many quantitative studies are looking to generalize results to a larger population, qualitative studies are instead looking to gather data on the perspectives of specific participants. Getting a large, representative sample is therefore less important than attracting participants whose perspectives will get you the data you need.
Here are a few of the most popular qualitative sampling techniques that you might consider.
- Creswell (2014) suggests being purposeful in identifying participants that might provide insight into your research question. Purposeful sampling involves selecting participants because you believe that they might contribute something to your analysis. For example, if your goal is to understand students’ experiences in a student organization, it may be useful work with a faculty advisor to get the organization’s roster. Using purposeful sampling strategies ensures that the perspectives of the students recruited provide the information needed to enhance your final conclusions.
- If you are trying to capture the perspectives of students from a wide variety of backgrounds, quota sampling may be appropriate. Quota sampling involves recruiting smaller groups of subjects based on some common criteria. Using our example of exploring the experiences of students in a specific student organization, you might consider recruiting for separate male and female focus groups, to make sure that you have a gender balance in the perspectives you collect. Quota sampling is usually used when the goal is to make sure participants match the overall population on specific demographic characteristics, like a stratified random sample in quantitative research. (Lohr, 2010)
- Either purposeful sampling or quota sampling may involve some form of convenience sampling, or using participants who might be readily available. Convenience sampling is sometimes derided, but it can be incredibly useful if your desired participants are already in an intact group. It would be really easy to gather information from a student organization if you were to go to one of those organization’s meetings, for example.
- Often times, an initial study may produce only a small number of participants. Many researchers may then employ a snowball sampling procedure to attract additional responses. Snowball sampling allows participants to act as recruiters, asking them to refer similar individuals whose perspective might be valuable. For example, if you have trouble finding other members of a student organization after your initial sampling, you might ask your first participants to recommend other group members for later interviews or focus groups. One increasingly popular version of snowball sampling is respondent-driven sampling, in which participants receive an incentive both for participating and for identifying additional students who be willing to participate. This strategy has been shown to be effective in recruiting participants from groups that may be difficult to find or unwilling to come forward (Heckathorn, 1997).
As with sampling in quantitative research, each of these sampling techniques carries with it certain assumptions and limitations that need to be considered. The references listed below can help you understand the assumptions and best practices for how to use them in your study.
Creswell, J. W. (2014). Research design: Qualitative, quantitative, and mixed methods approaches. Thousand Oaks, CA: Sage.
Heckathorn, D. D. (1997). Respondent-driven sampling: A new approach to the study of hidden populations. Social Problems, 44(2), 174-199.
Lohr, A. L. (2010). Sampling design and analysis. Boston, MS: Cengage Learning.