Fit a Heterogeneous Effect Forest for Observational Data — fit_observational_forest • heteff

Wraps grf::causal_forest() with a column-name interface and returns a unified heteff_fit object.

Usage

fit_observational_forest(
  data,
  outcome,
  treatment,
  covariates,
  num.trees = 2000,
  seed = 1,
  ...
)

Arguments

data: A data frame containing all required columns.
outcome: Name of the numeric outcome column.
treatment: Name of the binary or continuous treatment column.
covariates: Character vector of baseline covariate column names.
num.trees: Number of trees passed to grf::causal_forest().
seed: Random seed passed to grf::causal_forest().
...: Additional arguments passed to grf::causal_forest().

Value

A heteff_fit object with effect_table, fitted forest, and variable importance.

Examples

if (FALSE) { # \dontrun{
set.seed(1)
n <- 300
df <- data.frame(
  y = rnorm(n),
  w = rbinom(n, 1, 0.5),
  x1 = rnorm(n),
  x2 = rnorm(n)
)
fit <- fit_observational_forest(df, "y", "w", c("x1", "x2"))
head(as.data.frame(fit))
} # }