Understanding research synthesis (meta-analysis).

Synthesis of research findings has long been a part of reviewing and summarizing a field of study. Public health decisions are made on the available evidence. We summarize the approaches to research synthesis that draw on the best available evidence and the use of quantitative summaries through meta-analysis. We focus on observational studies. Heterogeneity offers the potential to observe a relation across study populations and circumstances. We emphasize the benefits of heterogeneity in overviews and the need to explore and describe the sources of heterogeneity. Random effects approaches to combining data are recommended, and the use of regression approaches is emphasized. Excluding studies with extreme results may bias a research synthesis and underestimate the true variance of the results, thus contributing to misleading inference. Thorough searching is the best guard against publication bias. We conclude with guidelines for combining epidemiological studies.