Professor Julian Higgins explains why he believes the systematic review and meta-analysis methods described in many highly cited papers are routinely misunderstood or misused.
Julian Higgins is Professor of Evidence Synthesis at the Bristol Evidence Synthesis, Appraisal and Modelling (BEAM) Centre at the University of Bristol. His research has focussed on the methodology of systematic review and meta-analysis and he has been senior editor of the Cochrane Handbook for Systematic Reviews of Interventions since 2003. He is an NIHR Senior Investigator and currently co-directs the NIHR Bristol Evidence Synthesis Group.
Systematic reviews and meta-analyses have become influential and popular. Papers describing aspects of the systematic review and meta-analysis toolkit have become some of the most highly cited papers. I will review those that appear at the top of the most-cited list and explain why I believe the methods described are routinely misunderstood or misused. These include a test for asymmetry in a funnel plot, the I-squared statistic for measuring inconsistency across studies, the random-effects meta-analysis model and the PRIMSA reporting guideline.
