Detecting small-study effects and funnel plot asymmetry in meta-analysis of survival data: A comparison of new and existing tests

Thomas P. A. Debray, Karel G. M. Moons, Richard D. Riley
  • Research Synthesis Methods, November 2017, Wiley
  • DOI: 10.1002/jrsm.1266

Methods for examining publication bias

What is it about?

This study compares several methods that can be used to examine whether a meta-analysis is affected by publication bias.

Why is it important?

Publication bias is a common threat in meta-analysis and may, for instance, occur when studies are more likely to be published if their results are statistically significant. If the presence of publication bias is ignored, summary results (e.g. treatment effects) are usually too extreme and can therefore be highly misleading.

Perspectives

Dr. Thomas Debray (Author)
Julius Center for Health Sciences and Primary Care

Detecting publication bias is difficult, and usually requires access to many published studies. Nevertheless, methods for evaluating funnel plot asymmetry may help to identify the likely presence of publication bias in a meta-analysis, and to assess the need for sensitivity analyses.

The following have contributed to this page: Dr. Thomas Debray