Power Analysis & Sample Size for Quantitative Research

by Nicholas Markette, Ed.D.

Power lifting is about moving the most amount of weight possible. Evaluating power lifters—power analysis—is pretty easy too! Simply total a lifter’s maximum bench press, deadlift, and squat weights and the lifter who moved the most weight wins. However, power analysis in quantitative research is a bit trickier. Knowing the appropriate sample size for quantitative research project requires a different type of power analysis. In quantitative research, a power analysis allows you to assess the population and determine what portion of it will provide statistically reliable data. What’s the minimum required sample size?

Statistically reliable sample sizes reduce the chance of Type I and Type II errors. A Type I error is the mistake of rejecting the null hypothesis when it is true. In other words, a pregnancy test that shows a woman is pregnant when she is not. A Type I error, in contrast, is a mistaken result that shows a negative result when it is positive. For example, a pregnancy test that shows negative when the woman is actually pregnant. A power analysis helps, reduce the potential for those errors.

One common tool that helps researchers conduct a power analysis is G*Power (See link for free download: https://www.psychologie.hhu.de/arbeitsgruppen/allgemeine-psychologie-und-arbeitspsychologie/gpower.html). G*Power enables researchers to calculate a sample size that reduces the chance for a Type I and II errors. Using the calculator will require a basic understanding of statistics and requires an understanding of alpha (α), the chance for a Type I error, and Power (1- β). If you need to learn about these concepts, reading Statistical Power Analysis for the Behavioral Sciences (1988) would be helpful.

When alpha and Power, along with the type of analysis tests planned (i.e., T-test, ANOVA, Regression, etc.), it is time to use G*Power to run the power analysis. This test will provide an estimate sample size for a proposed study. The following video makes this easy to understand:

APA citation:

Markette, N. & Markette., J. [Dr. Markette]. (2022, April). How to Use G*Power Calculator to Avoid Type I / Type 2 Errors || Quantitative Research Dissertations [Video]. https://youtu.be/PAQpq3MVPNM

Sources

Cohen, J. (1988). Statistical Power Analysis for the Behavioral Sciences (2nd ed.). Hillsdale, NJ: Lawrence Erlbaum Associates, Publishers.

Shop Recommendations