Package: WLogit 2.1

WLogit: Variable Selection in High-Dimensional Logistic Regression Models using a Whitening Approach

It proposes a novel variable selection approach in classification problem that takes into account the correlations that may exist between the predictors of the design matrix in a high-dimensional logistic model. Our approach consists in rewriting the initial high-dimensional logistic model to remove the correlation between the predictors and in applying the generalized Lasso criterion.

Authors:Wencan Zhu

WLogit_2.1.tar.gz
WLogit_2.1.zip(r-4.7)WLogit_2.1.zip(r-4.6)WLogit_2.1.zip(r-4.5)
WLogit_2.1.tgz(r-4.6-any)WLogit_2.1.tgz(r-4.5-any)
WLogit_2.1.tar.gz(r-4.7-any)WLogit_2.1.tar.gz(r-4.6-any)
WLogit_2.1.tgz(r-4.6-emscripten)
manual.pdf |manual.html✨
DESCRIPTION
card.svg |card.png
WLogit/json (API)

# Install 'WLogit' in R:

install.packages('WLogit', repos = c('https://clavie3009.r-universe.dev', 'https://cloud.r-project.org'))

Datasets:

beta - True coefficients in the esample.
test - WLogit output
X - Example of a design matrix of a logistic model
y - Example of a binary response variable of a logistic model.

On CRAN:

This package does not link to any Github/Gitlab/R-forge repository. No issue tracker or development information is available.

2.00 score 4 scripts 259 downloads 8 exports 98 dependencies

Last updated from:921ec1a7a4. Checks:7 WARNING, 2 OK. Indexed: yes.

Target	Result	Time
linux-devel-x86_64	WARNING	169
source / vignettes	OK	228
linux-release-x86_64	WARNING	174
macos-release-arm64	WARNING	142
macos-oldrel-arm64	WARNING	250
windows-devel	WARNING	116
windows-release	WARNING	116
windows-oldrel	WARNING	106
wasm-release	OK	164

Exports:CalculPx CalculWeight Refit_glm Thresholding top top_thresh WhiteningLogit WorkingResp

Dependencies:abind assertthat backports boot broom car carData cli codetools colorspace coop corpcor corrplot cowplot cpp11 cvCovEst data.table Deriv digest doBy dplyr farver foreach forecast Formula fracdiff future future.apply generics genlasso ggplot2 ggpubr ggrepel ggsci ggsignif glmnet globals glue gridExtra gtable igraph isoband iterators labeling lattice lifecycle listenv lme4 lmtest magrittr MASS Matrix MatrixModels matrixStats mgcv minqa modelr nlme nloptr nnet numDeriv origami parallelly pbkrtest pillar pkgconfig polynom purrr quantreg R6 rbibutils RColorBrewer Rcpp RcppArmadillo RcppEigen Rdpack reformulas rlang RMTstat RSpectra rstatix S7 scales shape SparseM stringi stringr survival tibble tidyr tidyselect timeDate urca utf8 vctrs viridisLite withr zoo

WLogit package

Introduction | Installation | Data generation | Correlation matrix $\boldsymbol{\Sigma}$ | Generation of $\boldsymbol{X}$ and $\boldsymbol{y}$ | Variable selection with the package | Estimation of $\boldsymbol{\beta}$ by $\widehat{\boldsymbol{\beta}}(\lambda)$ which maximizes the log-likelihood | Compare to Lasso

Rendered fromVignettes.Rmdusingknitr::knitr

Last update: 2023-07-17
Started: 2022-07-02

Help page	Topics
Variable Selection in High-Dimensional Logistic Regression Models using a Whitening Approach	WLogit-package WLogit
True coefficients in the esample.	beta
Calculate the class-conditional probabilities.	CalculPx
Calculate the weight	CalculWeight
Refit the logistic regression with chosen variables	Refit_glm
WLogit output	test
Thresholding on a vector	Thresholding
Thresholding to zero of the smallest values	top
Thresholding to a given threshold of the smallest values	top_thresh
Variable selection in high-dimensional logistic regression models using a whitening approach	WhiteningLogit
Calculate the working response	WorkingResp
Example of a design matrix of a logistic model	X
Example of a binary response variable of a logistic model.	y

Package: WLogit 2.1

WLogit: Variable Selection in High-Dimensional Logistic Regression Models using a Whitening Approach

Citation

Readme and manuals

Help Manual

Usage by other packages (reverse dependencies)