Stat Cafe - František Bartoš

less than 1 minute read

Time: Thursday 11/09/2023 from 12:00 PM to 1:00 PM
Location: BLOC 503
Food and drinks provided

Topic

Adjusting for Publication Bias in Meta-Analyses with Bayesian Model Averaging

Abstract

Publication bias is a ubiquitous threat to the validity of meta-analysis and the accumulation of scientific evidence. In order to estimate and counteract the impact of publication bias, multiple methods have been developed; however, simulation studies have shown the methods’ performance to depend on the true data-generating process, and no method consistently outperforms the others across a wide range of conditions.

In this talk, I introduce Robust Bayesian meta-analysis (RoBMA) that avoids the condition-dependent, all-or-none choice between competing methods and conflicting results. RoBMA model averages across two prominent approaches of adjusting for publication bias: (1) selection models of p-values and (2) models adjusting for small-study effects. The resulting model ensemble weights the estimates and the evidence for the absence/presence of the effect from the competing approaches with the support they receive from the data. Finally, I present applications and simulation studies evaluating the methodology.