get_scores.causal_survival_forest: Compute doubly robust scores for a causal survival forest.

View source: R/get_scores.R

get_scores.causal_survival_forestR Documentation

Compute doubly robust scores for a causal survival forest.

Description

For details see section 3.2 in the causal survival forest paper.

Usage

## S3 method for class 'causal_survival_forest'
get_scores(forest, subset = NULL, num.trees.for.weights = 500, ...)

Arguments

forest

A trained causal survival forest.

subset

Specifies subset of the training examples over which we estimate the ATE. WARNING: For valid statistical performance, the subset should be defined only using features Xi, not using the treatment Wi or the outcome Yi.

num.trees.for.weights

Number of trees used to estimate Var[W | X = x]. Note: this argument is only used in the case of a continuous treatment (see get_scores.causal_forest for details).

...

Additional arguments (currently ignored).

Value

A vector of scores.


grf documentation built on June 24, 2024, 5:20 p.m.