Retrospective power analysis

Abstract

Many papers have appeared in the recent biological literature encouraging us to incorporate statistical power analysis into our hypothesis testing protocol (Peterman 1990; Fairweather 1991; Muller & Benignus 1992; Taylor & Gerrodette 1993; Searcy-Bernal 1994; Thomas & Juanes 1996). The importance of doing a power analysis before beginning a study (prospective power analysis) is universally accepted: such analyses help us to decide how many samples are required to have a good chance of getting unambiguous results. In contrast, the role of power analysis after the data are collected and analyzed (retrospective power analysis) is controversial, as is evidenced by the papers of Reed and Blaustein (1995) and Hayes and Steidl (1997). The controversy is over the use of information from the sample data in retrospective power calculations. As I will show, the type of information used has fundamental implications for the value of such analyses. I compare the approaches to calculating retrospective power, noting the strengths and weaknesses of each, and make general recommendations as to how and when retrospective power analyses should be conducted.