ABSTRACT
Abstract Over the past decade, meta-analyses have played an increasingly important role in summarizing clinical information and informing policy. A new generation of meta-analysts have come forth, and the demand for a streamlined modeling approach has emerged. Compared with linear model estimation, many aspects of selecting and fitting models for meta-analysis involve nonstandard data structures and statistical assumptions. For example, each data point in the analysis-that is, each study-is associated with its own measure of precision which must be accounted for in the estimation process. Other study variables, such as design covariates, within-study predictors, and other aspects of the studies, also play an important role
when making inferences. Model selection therefore can be considerably facilitated by exploratory graphical analyses. In this chapter, we describe exploratory graphical methods. Also, we present a unified modeling approach to meta-analysis, one that integrates fixed-, random-and mixed-effect models, as well as Bayesian hierarchical models, into a single framework. Our approach places emphasis on model selection, estimation, fitting, diagnostics, and interpretation of results.
