Category: Post hoc power. Post hoc power represents a calculation of power after the data have been collected. These pages explain why this calculation is not appropriate. Articles are arranged by date with the most recent entries at the top. You can find the theme and closely related categories and other resources at the bottom of this page.

Stats: Post hoc power is never justified (May 13, 2005). Someone wrote in and was upset that a referee was insisting on post hoc power for all the outcome measures, and he only wanted to compute post hoc power for the negative outcomes (the outcomes that did not achieve statistical significance).

Stats: Post hoc power (November 1, 2002). Dear Professor Mean, The results of my study were negative, and the journal reviewer insists that I perform a post hoc power calculation. How do I do this?  -Jittery Jerry

Theme and closely related categories:

• Theme: Disseminating research results
• Category: Sample size justification
• Category: Writing research papers

Other resources:

• The abuse of power: the pervasive fallacy of power calculations for data analysis Description: This article demonstrates that several different approaches for calculating post-hoc power are flawed and can produce misleading conclusions. Once a confidence interval has been computed, there is no additional information that a post hoc power calculation can provide.
• The use of predicted confidence intervals when planning experiments and the misuse of power when interpreting results

[Return to full topic list] [Read current weblog entries]

This webpage was written by Steve Simon on 2007-09-11, edited by Steve Simon, and was last modified on 2008-07-08. Send feedback to ssimon at cmh dot edu or click on the email link at the top of the page.