calc_v_fold_marginal_ate: Calculate the v-fold specifice ATE for each rule found for...

In blind-contours/CVtreeMLE: Cross Validated Decision Trees with Targeted Maximum Likelihood Estimation

Calculate the v-fold specifice ATE for each rule found for individual mixture components.

Description

Aggregate marginal rules for each mixture variable found across the folds. For each rule extract the relevant nuisance parameter data calculated in the folds. Given the validation data estimates across the folds, for each tree do a TMLE update step to target the average treatment effect. Update the initial counterfactuals, calculate the influence curve and using the influence curve calculate variance estimates and p-values.

Usage

calc_v_fold_marginal_ate(marginal_data, mix_comps, marginal_rules, y, n_folds)

Arguments

marginal_data	List of dataframes of nuisance parameter data for each mixture
mix_comps	Vector of characters indicating the mixture components
marginal_rules	List of dataframes of marginal rules found across the folds
y	Vector indicating the Y
n_folds	Number of folds used in cross-validation

Value

A list of the marginal results for each fold including:

• marginal_results: A data frame with the data adpatively determined mixture component thresholds on the rows and ATE, variance, and RMSE estimates on the columns.

• data: A list of data frames for each mixture component threshold evaluated as the exposure, baseline covariates, outcome, nuisance parameter estimates, marginal ATE and the influence curve.

blind-contours/CVtreeMLE documentation built on June 22, 2024, 8:53 p.m.