Estimate nuisance models (outcome, treatment, and missingness) and calculate CATE hats using k-fold cross validation

Usage

learn_nuisance(
  df,
  Y_name,
  A_name,
  W_list,
  id_name = NULL,
  sl.library.outcome,
  sl.library.treatment,
  sl.library.missingness,
  outcome_type,
  k_folds = 2,
  ps_trunc_level = 0.01
)

Arguments

df: dataframe containing full dataset
Y_name: name of outcome variable in df
A_name: name of treatment variable in df
W_list: character vector containing names of covariates in the dataframe to be used for fitting nuisance models
id_name: name of patient id variable in dataset if applicable, will default to NULL and use observation index
sl.library.outcome: character vector of SuperLearner libraries to use to fit the outcome models
sl.library.treatment: character vector of SuperLearner libraries to use to fit the treatment models
sl.library.missingness: character vector of SuperLearner libraries to use to fit the missingness models
outcome_type: specifying continuous (outcome_type = "gaussian") or binary (outcome_type = "binomial") outcome Y
k_folds: number of folds for k_fold cross validation
ps_trunc_level: numeric level to use for truncation of any predicted values that fall below it

Value

k_fold_nuisance: list of `Nuisance` objects (fit nuisance models) for each of k folds
k_fold_assign_and_CATE: dataframe of CATE estimates, k-1 folds, pseudo-outcome, and shuffle idx corresponding to validRows for each observation
validRows: list of innerCV SuperLearner row assignments for each training set
fold_assignments: dataframe containing fold assignments for each id