A Bayesian Nonparametric Meta-Analysis Model

TL;DR

This paper introduces a Bayesian nonparametric meta-analysis model that flexibly captures diverse effect-size distributions, improving prediction accuracy over traditional normal-based models in behavioral-genetic research.

Contribution

The paper presents a novel Bayesian nonparametric approach for meta-analysis, allowing for more accurate modeling of complex effect-size distributions beyond normal assumptions.

Findings

The model effectively captures unimodal, skewed, and multimodal distributions.

It outperforms traditional models in predictive accuracy.

Application to behavioral-genetic data demonstrates practical utility.

Abstract

In a meta-analysis, it is important to specify a model that adequately describes the effect-size distribution of the underlying population of studies. The conventional normal fixed-effect and normal random-effects models assume a normal effect-size population distribution, conditionally on parameters and covariates. For estimating the mean overall effect size, such models may be adequate, but for prediction they surely are not if the effect size distribution exhibits non-normal behavior. To address this issue, we propose a Bayesian nonparametric meta-analysis model, which can describe a wider range of effect-size distributions, including unimodal symmetric distributions, as well as skewed and more multimodal distributions. We demonstrate our model through the analysis of real meta-analytic data arising from behavioral-genetic research. We compare the predictive performance of the Bayesian nonparametric model against various conventional and more modern normal fixed-effects and random-effects models.