Power and Sample Size
Power is “the probability of rejecting the null hypothesis in a statistical test when a particular alternative hypothesis happens to be true” (Merriam-Webster Dictionary). Here, we discuss why power is needed in clinical research; the properties of power—including sample size, variability, frequency, p-value, and effect size; whether statistical power can ever be truly known; and how to calculate statistical power. Power is a theoretical concept, but it has practical benefit. Overpowered studies are inefficient and may waste resources that could be used to further our knowledge in other ways. Conversely, underpowered studies not only waste the time of participants and the researchers, they may violate the responsibility to do no harm as the study intervention may not be risk-free. All studies, especially those in which invasive interventions are being used, should always, ethically, be adequately powered.
- 1.Adcock CJ. Sample size determination: a review. Statistician. 1997;46(2):261–83.Google Scholar
- 6.“Power.” Merriam-Webster.com. 2018. https://www.merriam-webster.com (1 July 2018).
- 8.Sim J, Wright CC. The Kappa statistic in reliability studies: use, interpretation, and sample size requirements. Phys Ther. 2005;85(3):257–68.Google Scholar