Meta-CART: A Flexible Approach to Identify Moderators in Meta-Analysis

Meta-CART integrates classification and regression trees (CART) into meta-analysis. Meta-CART is a flexible approach to identify interaction effects between moderators in meta-analysis. The method is described in Dusseldorp et al. (2014) and Li et al. (2017) .


Changes in metacart Version 2.0-0 (2018-11-21)

  • New plot.FEmrt() function that produces the same plots as plot.REmrt().
  • New REmrt() function that implements the update scheme to boost the speed. Also, internal Rcpp functions .compute_tau_() and .compute_re_Q_() were created to speed up the computation of residual heterogeneity and Q-statistic for each split point.
  • Xvalid_all() is renewed with faster speed. Internal Rcpp functions .partition(), .ComputeY(), .PredY(), .ReplaceNA() were added.
  • quint.validate() is renewed.
  • New example data set dat.balanced is added.

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


2.0-3 by Juan Claramunt, a year ago

Browse source code at

Authors: Xinru Li [aut, cre] , Elise Dusseldorp [aut, cph] , Kaihua Liu [ctb] (supported with the plot function) , Juan Claramunt [ctb] , Jacqueline Meulman [ctb]

Documentation:   PDF Manual  

Task views: Meta-Analysis

GPL (>= 2) license

Imports Rcpp

Depends on stats, ggplot2, gridExtra, methods, rpart

Linking to Rcpp

See at CRAN