Meta-Analysis

This feature requires the Statistics Base option.

Meta analysis is the analysis of the data obtained from a collection of studies that answer similar research questions. These studies are known as primary studies. Meta analysis uses statistical methods to produce an overall estimate of an effect, explore between-study heterogeneity, and investigate the impact of publication bias or, more generally, small-study effects on the final results.

IBM® SPSS® Statistics supports standard effect sizes and generic (pre-calculated) effect sizes for both binary data (such as the log odds-ratio) and for continuous data (such as Hedges’s g). Meta analysis information (such as the study-specific effect sizes and their corresponding standard errors and the meta-analysis model and method) is specified during the meta analysis declaration step. The information is automatically used by all subsequent meta analysis.

Random effects, common effect, and fixed effects meta analysis models are supported. Depending on the chosen meta analysis model, the various estimation methods (for example inverse-variance and Mantel–Haenszel) are available for the common effect and fixed effects models. Several different estimators are also available for the between study variance parameter for the random effects model.