Adjusting for Outcome Reporting Bias in Meta-analysis: A Multiple Imputation Approach

2026-07-08

AI Summary

This study addresses outcome reporting bias (ORB) in meta-analysis—a pervasive issue arising from selective reporting of study outcomes, which distorts treatment effect estimates. The work proposes the first systematic application of multiple imputation to correct for ORB, accommodating both univariate and multivariate meta-analytic settings. By leveraging correlations among outcomes within a multivariate framework, the method enables information sharing across reported and missing endpoints. It models missing outcomes under assumed mechanisms of selective non-reporting and incorporates sensitivity analyses to ensure robust inference. Validation through real clinical datasets and simulation studies demonstrates that the corrected effect estimates consistently shift toward more conservative values, with the magnitude of adjustment modulated by the strength of the selection mechanism and between-study heterogeneity. This approach effectively mitigates the detrimental impact of ORB on the credibility of meta-analytic conclusions.

Abstract

Background: Outcome reporting bias (ORB) occurs when study outcomes are selectively reported based on their results. ORB potentially undermines the credibility and validity of meta-analyses and contributes to research waste by distorting overall treatment effects. ORB can be viewed as a missing data problem in which unreported study outcomes introduce bias. Despite the serious implications ORB poses, it remains an underrecognized issue, with only a few adjustment methods available. Methods: We propose an approach that addresses unreported study outcomes in meta-analyses through multiple imputation for univariate and multivariate meta-analysis. To assess the impact of ORB in meta-analyses, we apply our proposed methodology to real clinical data affected by ORB, and conduct a simulation study to evaluate the method's performance under a range of scenarios. Results: The proposed method provides bias-adjusted estimates under assumed selective non-reporting mechanisms. In the application to clinical data, ORB-adjusted estimates were systematically shifted towards less extreme treatment effects compared with naive analyses, highlighting the potential magnitude of ORB in practice. The simulation study shows that the extent of adjustment depends on the assumed selection mechanism and the degree of heterogeneity, with stronger selection leading to larger adjustment. Conclusions: Imputing unreported study outcomes provides a promising approach to address ORB in meta-analyses. The multivariate approach extends ORB adjustment to jointly model correlated outcomes, allowing borrowing of strength across outcomes. Overall, we propose a practical and flexible approach for evaluating the sensitivity of univariate and multivariate meta-analytic conclusions to ORB.

Problem

• outcome reporting bias
• meta-analysis
• missing data
• selective reporting
• treatment effect

Innovation

• multiple imputation
• outcome reporting bias
• meta-analysis
• missing data
• multivariate meta-analysis