Comprehensive meta analysis moderator analysis software#
In the meta-analysis framework, moderator analysis can be conducted with several stand-alone software programs such as Comprehensive Meta-Analysis (Borenstein et al., 2009), Meta-Analyst (Wallace et al., 2009), and the Cochrane Collaboration’s RevMan (Collaboration, 2014). The relationship between moderators and the study effect sizes can be of high interest for behavioral scientists to evaluate existing interventions and to design new potentially effective interventions. The typical goals of meta-analysis are to estimate the overall effect size (i.e., a weighted average of study effect sizes), to quantity the heterogeneity in the study effect sizes, and to investigate the study characteristics that explain the heterogeneity (i.e., moderators). Methodology for synthesizing findings from multiple studies addressing the same research question has a long history (Hedges, 1981 Hedges & Olkin, 1985). The application of the package is illustrated step-by-step using diverse examples. In addition, a new look ahead procedure is presented. This package can fit both fixed- and random-effects meta-CART, and can handle dichotomous, categorical, ordinal and continuous moderators. This paper describes the R-package metacart, which provides user-friendly functions to conduct meta-CART analyses in R. The analysis result is a tree model in which the studies are partitioned into more homogeneous subgroups by combinations of moderators. The method meta-CART was recently proposed to identify interactions between multiple moderators. However, in most meta-analysis studies, interaction effects are neglected due to the lack of appropriate methods. When there are multiple moderators, they may amplify or attenuate each other’s effect on treatment effectiveness. Knowledge about study features (i.e., moderators) that can explain the heterogeneity in effect sizes can be useful for researchers to assess the effectiveness of existing interventions and design new potentially effective interventions. In meta-analysis, heterogeneity often exists between studies.