In yang0117/TVsMiss: Variable Selection for Missing Data

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "README-"
)

TVsMiss

The goal of TVsMiss is to select variable in both low and high dimesion through regularization likelihood method.

Installation

You can install TVsMiss from github with:

# install.packages("devtools")
devtools::install_github("yang0117/TVsMiss")

Example

rm(list = ls())
library(TVsMiss)
n <- 50
p <- 8
beta <- c(3,0,1.5,0,2,rep(0,p-5))
xm <- matrix(rnorm(n*p),ncol = p, nrow = n)
y <- xm %*% beta + rnorm(n)
colnames(xm) <- paste0("Var_",1:p)
fit02 <- tvsmiss(x=xm,y=y,method = "BIC")
fit02$selection_beta
plot(fit02,x.log=TRUE,label = TRUE)