View source: R/test_hte_crump.R
| test_constant_cate | R Documentation |
H0': tau(x) = tau for some tau and all x.
test_constant_cate(
Y,
W,
X,
poly_order = 1L,
covariate_select = c("all", "top_down", "bottom_up"),
t_threshold = 2,
regression = c("ols", "logistic", "poisson"),
offset = NULL
)
Y |
Numeric outcome vector. |
W |
Treatment indicator (0/1). |
X |
Numeric covariate matrix (no factors; use
|
poly_order |
Integer. Default: 1. |
covariate_select |
"all", "top_down", or "bottom_up". |
t_threshold |
Numeric. Default: 2.0. |
regression |
"ols", "logistic", or "poisson". |
offset |
Numeric offset vector (Poisson only). |
A list with components test, chi_sq, df,
p_value_chi, normal (normal-approximation statistic),
p_value_normal, K (number of covariates), N0,
N1, regression, covariates_selected,
ate_diff (intercept-difference point estimate), and
diff_slope, V_slope. Returns NULL if per-arm
fits fail or fewer than two covariates are retained.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.