Model averaging for robust extrapolation in evidence synthesis

TL;DR

This paper introduces a robust model-averaging method using heavy-tailed mixture priors for effect estimation in meta-analysis, especially when extrapolating from source to target data with limited studies.

Contribution

It develops a simple, robust extrapolation strategy with explicit handling of prior-data conflicts, demonstrated through simulations and provided with accessible R code.

Findings

Method effectively handles prior-data conflicts.

Demonstrates robustness in simulation studies.

Easily implementable with provided R code.

Abstract

Extrapolation from a source to a target, e.g., from adults to children, is a promising approach to utilizing external information when data are sparse. In the context of meta-analysis, one is commonly faced with a small number of studies, while potentially relevant additional information may also be available. Here we describe a simple extrapolation strategy using heavy-tailed mixture priors for effect estimation in meta-analysis, which effectively results in a model-averaging technique. The described method is robust in the sense that a potential prior-data conflict, i.e., a discrepancy between source and target data, is explicitly anticipated. The aim of this paper to develop a solution for this particular application, to showcase the ease of implementation by providing R code, and to demonstrate the robustness of the general approach in simulations.