ABSTRACT
A meta-analysis is a group of statistical techniques that are concerned with the pooling of the results from individual studies to obtain a single overall estimate of treatment effect. A meta-analysis can provide more precise estimates of the effects of an intervention than those derived from the individual studies included in a review. To examine the relative effect of different interventions, ideally systematic reviews and meta-analyses should be based on randomized controlled trials. Typically, a meta-analysis has two fundamental goals: testing the homogeneity of the studies from which the results are obtained, and obtaining a combined summary measure of the effect size of the studied relation, together with measures of uncertainty, a confidence interval, and its statistical significance. The great majority of meta-analyses one can find in perusing medical literature concern results of controlled clinical trials. Most systematic reviews and meta-analyses rely on extracting aggregate trial data from trial reports in the form of peer-reviewed articles or presentations.
