Doubly-Robust Scores

Source: R/utils.R

Constructs doubly-robust scores via K-fold cross-fitting.

dr_scores(Y, D, X, k = 5)

Arguments

Y

Outcome vector.

D

Treatment assignment vector.

X

Covariate matrix (no intercept).

k

Number of folds.

Value

A vector of scores.

Details

Honest regression forests are used to estimate the propensity score and the conditional mean function of the outcome.

Author

Riccardo Di Francesco