Conducting Power Analysis for Meta-Analysis of Dependent Effect Sizes: Common Guidelines and an Introduction to the POMADE R package
Date created: | Last Updated:
: DOI | ARK
Creating DOI. Please wait...
Description: In a recent paper Vembye, Pustejovsky, & Pigott (2022) developed power approximation formulas for meta-analysis of dependent effect sizes across the multi-level meta-analysis (MLMA), the correlated effects (CE), and the correlated-hierarchical effects (CHE) models. However, this paper was rather technically and esoterically written possibly limiting the general use of the developed methods among applied reviewers and meta-analysis. Moreover, the paper mainly focused on the statistical accuracy and quality assurance of the performance of the newly developed methods and less on the practical challenges encountered by reviewers for obtaining the relevant quantities required to conduct reliable power approximations for meta-analyses with dependent effect sizes. With this article, we aim to remedy this challenge by putting forward common guidelines for how we think power approximation for meta-analyses of dependent effect sizes could be conducted. The ultimate goal is to make the power approximation formulas digestible and accessible for the applied reviewer and/or meta-analyst.