Classification Based MCAR Test

Implementation of a KL-based (Kullback-Leibler) test for MCAR (Missing Completely At Random) in the context of missing data as introduced in Michel et al. (2021) .

PKLMtest: testing MCAR with classification

Overview

PKLMtest is a package intended to provide a framework for testing MCAR with classification. It implements the test described in Michel, Naef, Spohn and Meinshausen. 2021 . Examples of use of the library are shown below.

Installation

To install the package from github you can run

install.packages("devtools")
devtools::install_github("missValTeam/PKLMtest")

Examples:

n <- 500 
X <- cbind(rnorm(n),rnorm(n))
X.NA <- X
X.NA[,1] <- ifelse(stats::runif(n)<=0.2, NA, X[,1])
pval <- PKLMtest(X)

Issues

To report an issue, please use the issue tracker on github.com.