Estimates from individual studies included in a meta-analysis often are not in agreement, giving rise to statistical heterogeneity. In such cases, exploration of the causes of heterogeneity can advance knowledge by formulating novel hypotheses. We present a new method for visualizing between-study heterogeneity using combinatorial meta-analysis. The method is based on performing separate meta-analyses on all possible subsets of studies in a meta-analysis. We use the summary effect sizes and other statistics produced by the all-subsets meta-analyses to generate graphs that can be used to investigate heterogeneity, identify influential studies, and explore subgroup effects. This graphical approach complements alternative graphical explorations of data. We apply the method to numerous biomedical examples, to allow readers to develop intuition on the interpretation of the all-subsets graphical display. The proposed graphical approach may be useful for exploratory data analysis in systematic reviews. Copyright © 2012 John Wiley & Sons, Ltd.
Stored only when both papers are in the corpus — 270 citations exist upstream.