process_missing: Preprocess Data to Handle Missing Variables

In lurui0421/Super-Learning-: The Extensible TMLE Framework

Description

Process data to account for missingness in preparation for TMLE

Usage

process_missing(data, node_list, complete_nodes = c("A", "Y"),
  impute_nodes = NULL, max_p_missing = 0.5)

Arguments

data,	data.table, containing the missing variables
node_list,	list, what variables comprise each node
complete_nodes,	character vector, nodes we must observe
impute_nodes,	character vector, nodes we will impute
max_p_missing,	numeric, what proportion of missing is tolerable? Beyond that, the variable will be dropped from the analysis

Details

Rows where there is missingness in any of the complete_nodes will be dropped. Then, missingness will be median-imputed for the variables in the impute_nodes. Indicator variables of missingness will be generated for these nodes.

Then covariates will be processed as follows:

1. any covariate with more than max_p_missing missingness will be dropped

2. indicators of missingness will be generated

3. missing values will be median-imputed

Value

list containing the following elements:

• data, the updated dataset

• node_list, the updated list of nodes

• n_dropped, the number of observations dropped

• dropped_cols, the variables dropped due to excessive missingness

lurui0421/Super-Learning- documentation built on July 4, 2019, 1:02 p.m.