How much data is enough?
Focus on what you need to make decisions
When considering how much evidence you should collect, consider the overall question that guides the inquiry, and how the results will be applied. If you are planning a programmatic overhaul, then you’ll probably want a larger sample with a lower error margin. However, the larger the sample, the greater the commitment of time required from faculty. A smaller sample is acceptable if the results will be used to inform minor curricular changes.
Your goal should be to gather a sample about which you will feel confident in using the results to inform program decisions. Suskie (2009) suggests: “collect enough evidence to feel reasonably confident that you have a representative sample of what your students have learned and can do” (p. 47).
- “Simple” random samples are a straightforward way to obtain a representative sample as they give every student an equal chance of being selected.
- Cluster random samples can be used with larger groups in the same fashion, by choosing a random sample of subgroups of students and collecting information from everyone in each subgroup.
- Purposeful or judgment samples are “carefully, but not randomly chosen so that, in your judgment, they are representative of the students you are assessing” (Suskie, 2009, p. 49-50).