adaptest_old: OLD Data-Adaptive Algorithm Implementation (for reference...

Description Usage Arguments Value Author(s)

View source: R/adaptest_old.R

Description

Performs targeted minimum loss-based estimation (TMLE )of a marginal additive treatment effect of a binary point treatment on an outcome. The data-adaptive algorithm is used to perform variable reduction to avoid the disadvantages associated with multiple testing. INTERNAL USE ONLY.

Usage

1
2
3
4
adaptest_old(Y, A, W = NULL, n_top, n_fold, folds_vec = NULL,
  parameter_wrapper = adaptest::rank_DE, learning_library = c("SL.glm",
  "SL.step", "SL.glm.interaction", "SL.gam", "SL.earth"),
  absolute = FALSE, negative = FALSE)

Arguments

Y

continuous or binary outcome variable

A

binary treatment indicator: 1 = treatment, 0 = control

W

matrix containing baseline covariates

n_top

integer value for the number of candidate covariates to generate using the data-adaptive estimation algorithm

n_fold

integer number of folds to be used for cross-validation

folds_vec

Vector of numeric indicating the validation fold in which a given observation falls for a standard V-fold cross-validation procedure. Default is NULL, in which case a custom cross-validation procedure is used.

parameter_wrapper

function

learning_library

character

absolute

boolean: TRUE = test for absolute effect size. This FALSE = test for directional effect. This overrides argument negative.

negative

boolean: TRUE = test for negative effect size, FALSE = test for positive effect size

Value

S3 object of class "data_adapt" for data-adaptive multiple testing.

Author(s)

Wilson Cai wcai@berkeley.edu, in collaboration with Alan E. Hubbard, with contributions from Nima S. Hejazi.


adaptest documentation built on April 28, 2020, 7:24 p.m.