A fundamental part of the design of any study is the consideration of the number of individuals, “experimental units,” or observations that are required to appropriately conduct the research. Unfortunately, even if we think some treatment or intervention is successful as compared to another with respect to an outcome, due to sampling and variability within a population of interest, we may not actually observe that success statistically in a given study. However, for example, one may specify that they want to have an 80% chance of detecting some effect if that effect truly exists. Such a study would be said to have 80% power to detect the specified effect. The investigators would then calculate a sample size based on this power requirement (along with other statistical and scientific considerations). In contrast, due to cost constraints, ethical or other considerations, one may be only able to obtain a fixed sample size for a study. In this latter case, one may wish to calculate the power of a test, given the prespecified sample size.