Understanding statistical power

J Orthop Sports Phys Ther. 2001 Jun;31(6):307-15. doi: 10.2519/jospt.2001.31.6.307.

Abstract

This article provides an introduction to power analysis so that readers have a basis for understanding the importance of statistical power when planning research and interpreting the results. A simple hypothetical study is used as the context for discussion. The concepts of false findings and missed findings are introduced as a way of thinking about type I and type II errors. The primary factors that affect power are described and examples are provided. Finally, examples are presented to demonstrate 2 uses of power analysis, 1 for prospectively estimating the sample size needed to insure finding effects of a known magnitude in a study and 1 for retrospectively estimating power to gauge the likelihood that an effect was missed.

Publication types

  • Review

MeSH terms

  • Data Interpretation, Statistical*
  • Humans
  • Observer Variation
  • Research Design*
  • Sample Size
  • Statistical Distributions