Meta-CART: A Flexible Approach to Identify Moderators in Meta-Analysis
A function to draw the confidence interval as a diamond
A function to compute RE Q-between
Compute re Q for different values of tau2
Compute tau2
Compute the subgroup effect sizes
Partition the test set based on a trained tree
Predict effect size for the test set
Replace missing values by the overall weighted mean
A function to deal with symbols
Fixed effect meta-tree
A function to find the optimal combination of first two splits, and th...
A function to find the best triplets of parent, moderator, and split p...
A function to list all possible split points for the first split
R package for meta-CART
A function to draw an oval
Visualisation of a FE meta-tree
Visualisation of a RE meta-tree
Predictions from a fitted metacart object
Predictions from a fitted metacart object
A function to parition newdata based on the fitted model
Print function for FEmrt
Print function for REmrt
A function to find the split point
Random effects meta-tree
A function to fit the tree with look-ahead option
Summary of the results of a FE meta-tree object
Summary of the results of a RE meta-tree object
Prune a tree
A function to update node
A function to compute cross-validation errors
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) <doi:10.1037/hea0000018> and Li et al. (2017) <doi:10.1111/bmsp.12088>.