How to conduct a meta-analysis in hand surgery. Part II: heterogeneity and publication bias.

Abstract

This is the second part of a two-part article on pitfalls in meta-analysis in hand surgery. The purpose of this second part is to introduce the concepts of heterogeneity and publication bias and to describe how these problems should be analysed and addressed when conducting meta-analyses in hand surgery. Statistical heterogeneity, which occurs when the variability in the observed effect cannot be explained by sampling variability alone, may be caused by clinical heterogeneity, methodological heterogeneity or both. A common error in hand surgery meta-analyses is the failure to adequately investigate the sources of heterogeneity. Heterogeneity is also associated with publication bias. Understanding heterogeneity in published meta-analyses would help in the understanding of the available evidence in Hand Surgery.