Power calculations in genetic studies

Abstract

The power of a statistical test is the probability that it will yield a statistically significant result given that the null hypothesis is false. In other words, it represents the chance that the study will be successful in detecting a true effect and is dependent on a number of factors, including the magnitude of the effect, the sample size and study design, and the specified false-positive rate. Power calculations are primarily performed during the planning stages of a study, most typically in determining the sample size required. Consideration of statistical power can also sometimes shed light on the results of completed studies, particularly in the interpretation of negative results. In this article, we review the fundamentals of statistical power, discuss how power is calculated (using a genetic case/control study as an example), and consider the most pertinent factors that influence power in genetic studies. Finally, we focus on power in the context of modern whole-genome association studies, in which issues of coverage, multiple testing, and staged designs are paramount.