## Generate data.
set.seed(1986)
n <- 1000
k <- 3
X <- matrix(rnorm(n * k), ncol = k)
colnames(X) <- paste0("x", seq_len(k))
D <- rbinom(n, size = 1, prob = 0.5)
mu0 <- 0.5 * X[, 1]
mu1 <- 0.5 * X[, 1] + X[, 2]
Y <- mu0 + D * (mu1 - mu0) + rnorm(n)
## Training-honest sample split.
honest_frac <- 0.5
splits <- sample_split(length(Y), training_frac = (1 - honest_frac))
training_idx <- splits$training_idx
honest_idx <- splits$honest_idx
Y_tr <- Y[training_idx]
D_tr <- D[training_idx]
X_tr <- X[training_idx, ]
Y_hon <- Y[honest_idx]
D_hon <- D[honest_idx]
X_hon <- X[honest_idx, ]
## Construct sequence of groupings. CATEs estimated internally.
groupings <- build_aggtree(Y_tr, D_tr, X_tr,
Y_hon, D_hon, X_hon)
## Analyze results with 4 groups.
results <- inference_aggtree(groupings, n_groups = 4)
## Print results.
print(results, table = "diff")
print(results, table = "avg_char")
Run the code above in your browser using DataLab