generate_rules: Generate rules

In CRE: Interpretable Discovery and Inference of Heterogeneous Treatment Effects

Generate rules

Description

Generates a list of rules characterizing the heterogeneity in the Conditional Average Treatment Effect (CATE) by tree-based methods (i.e., random forest).

Usage

generate_rules(X, ite, ntrees, node_size, max_rules, max_depth)

Arguments

X	A covariate matrix.
ite	A vector of estimated ITE.
ntrees	The number of decision trees for the random forest algorithm.
node_size	Minimum size of the trees' terminal nodes.
max_rules	Maximum number of candidate decision rules.
max_depth	Maximum rules length.

Value

A list of rules (names).

CRE documentation built on Oct. 19, 2024, 5:07 p.m.