When I was in graduate school, I had a professor whose area of interest was sample size. He published a great article on the topic (see citation below), and I find myself thinking back on the key points of it every time I am asked the question “How big of a sample do I need?”
As Dr. Lenth says, “An undersized study can be a waste of resources for not having the capability to produce useful results, while an oversized one uses more resources than are necessary.” Studies that are “too big” also have the potential to come back with every variable being statistically significant — even those variables that are of little actual importance. Clearly, finding the right sample size for your program is important but can be a balancing act! To make it easier, there are questions you can ask to help figure out what sample size is appropriate.
· Exactly what are the goals of this study?
· What do you estimate the response rate will be?
· What timeframe do you have for collecting data?
· What will happen if we don’t get the right sample size?
· Does the scope of the study need to be narrowed due to limited sample?
There is no “one size fits all” when it comes to sample size. Each program will have its own requirements; hopefully, remembering to ask a few easy questions will make finding the right one for you a relatively painless process.
Citation: Lenth, Russell V. "Some Practical Guidelines for Effective Sample Size Determination." The American Statistician. August 2001, Vol. 55, No. 3:187-193.