Meta-análisis de correlaciones y meta-regresión en R: Guía práctica [Meta-analysis of correlations and meta-regression in R: A Practical Guide]

Abstract

Meta-analysis is a widely used method to synthesise data from different studies. However, students, practitioners and researchers often lack the practical knowledge to perform and interpret a meta-analysis. This guide presents a variety of tools for performing meta-analysis of correlations in R, using real examples. It ranges from simple analyses and their interpretation, to moderator analysis (meta-regression), using the packages metafor (Viechtbauer, 2010) and metaviz (Kossmeier et al., 2020). It also includes explanations for transforming Pearson’s r coefficients to Fisher’s z (and vice versa), creating forest plots and funnel plots, heterogeneity analysis and influence diagnostics, as well as strategies for detecting potential publication bias using the weightr package (Coburn & Vevea, 2019), and for determining the statistical power of a meta-analysis using metafor (Quintana, 2022). With this guide, readers will be able to acquire the necessary skills to perform meta-analysis of correlations effectively in R and obtain reliable results.

Juan David Leongómez

Associate Professor

My research interests include mate choice and human vocal communication, with an aspiration towards understanding musicality. I am also interested in bioacoustics and psychoacoustics, as well as statistics and  programming.