Meta-analysis: quantitative integration of independent research results

Abstract

Meta-analysis, a quantitative method of combining the results of independent research studies, is described as a method for reviewing research literature. Four steps are taken to summarize the research in an area. First, a thorough literature review is conducted to identify a group of research studies with the relevant treatment variable. Second, an effect size is calculated for each study. Third, an overall (composite) effect size is determined by a weighted combination of the obtained effect sizes. Fourth, a fail-safe N (the number of unpublished studies with opposing conclusions needed to negate the published literature) is calculated to assess the certainty of the overall effect size. Meta-analysis was applied to 33 studies of chymopapain in an illustrative example. The analysis produced a large effect size of 0.8082 and a fail-safe N of 214, indicating strong support for the effectiveness of the treatment with chymopapain. Meta-analysis can be a useful tool if it is used properly. It is particularly useful as an adjunct to other methods of review that are used in pharmacy practice.