ate: Estimate average treatment effects using a causal forest

In ensley-nexant/cfeval: Causal Forest Evaluation and Visualization

Description

A thin wrapper around average_treatment_effect. Defines the ate class so that confidence intervals and plots can be created using generics.

Usage

ate(fit, ...)

Arguments

fit	A trained causal_forest object
...	Additional parameters to be passed to average_treatment_effect

Value

An instance of the ate class, which is essentialy a one-row tibble with columns estimate and std.err

Examples

## Not run: 
 require(grf)

 n <- 2000; p <- 10

 X <- matrix(rnorm(n * p), n, p)
 W <- rbinom(n, 1, 0.4 + 0.2 * (X[, 1] > 0))
 Y <- pmax(X[, 1], 0) * W + X[, 2] + pmin(X[, 3], 0) + rnorm(n)

 cf <- causal_forest(X, Y, W)
 a <- ate(cf, target.sample = 'treated')

## End(Not run)

ensley-nexant/cfeval documentation built on May 20, 2020, 12:34 a.m.