Supplementary Material for Robust Recursive Partitioning for Heterogeneous Treatment Effects with Uncertainty Quantification A Preliminaries of Conformal Prediction

Here, we provide a basic idea of conformal prediction to help understanding. Since the samples are i.i.d., for a new In these methods, the subgroups (i.e., leaves in the tree structure) are constructed; For recursive partitioning, various criteria have been proposed. In the criterion, the training samples are split into two subsets; One is used to build a tree structure and another one is used to estimate the treatment effects. 's is determined by the design functions. There is no redundant covariate which has no effect on the outcomes.