On the Post Hoc Power in Testing Mean Differences

164 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Sample size planning for statistical power and accuracy in parameter estimation. (2008, background): “F o r p er so n al u se o n ly . hoc power is that Yuan & Maxwell (2005) have shown that post hoc power does not necessarily provide a good estimate of the actual population power even in large samples.”
Replication, statistical consistency, and publication bias. (2013, background): “Yuan and Maxwell (2005) showed that such estimates are expected to be compressed around 0.5, relative to the true power value.”
MorePower 6.0 for ANOVA with relational confidence intervals and Bayesian analysis (2012, methodology): “Second, post hoc analysis of power may be useful after a study is completed in order to evaluate whether there was adequate power to detect a relevant population effect size (Faul et al., 2007; Yuan & Maxwell, 2005, p. 142).”
Estimating Population Mean Power Under Conditions of Heterogeneity and Selection for Significance (2020, background): “The main problem is that estimates for a single result are too variable to be practically useful (Yuan & Maxwell, 2005; but see Anderson, Kelley, & Maxwell, 2017).”
Sample Size Justification (2021, unknown): “Since reporting post-hoc power is just a different way of reporting the p value, reporting the post-hoc power will not provide an answer to the question editors are asking (Hoenig & Heisey, 2001; Lenth, 2007; Schulz & Grimes, 2005; Yuan & Maxwell, 2005).”