Fixed- and random-effects models in meta-analysis

There are 2 families of statistical procedures in meta-analysis: fixed- and random-effects procedures. They were developed for somewhat different infe rence goals: making inferences about the effect parameters in the studies t hat have been observed versus making inferences about the distribution of e ffect parameters in a population of studies from a random sample of studies . The authors evaluate the performance of confidence intervals and hypothes is tests when each type of statistical procedure is used for each type of i nference and confirm that each procedure is best for making the kind of inf erence for which it was designed. Conditionally random-effects procedures ( a hybrid type) are shown to have properties in between those of fixed- and random-effects procedures.