stepSplitReg: Stepwise Split Regularized Regression

Functions to perform stepwise split regularized regression. The approach first uses a stepwise algorithm to split the variables into the models with a goodness of fit criterion, and then regularization is applied to each model. The weights of the models in the ensemble are determined based on a criterion selected by the user.

Version: 1.0.3
Imports: Rcpp (≥ 1.0.7), SplitGLM, nnls
LinkingTo: Rcpp, RcppArmadillo
Suggests: testthat, mvnfast
Published: 2022-11-22
DOI: 10.32614/CRAN.package.stepSplitReg
Author: Anthony Christidis [aut, cre], Stefan Van Aelst [aut], Ruben Zamar [aut]
Maintainer: Anthony Christidis <anthony.christidis at stat.ubc.ca>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: yes
Materials: README NEWS
CRAN checks: stepSplitReg results

Documentation:

Reference manual: stepSplitReg.pdf

Downloads:

Package source: stepSplitReg_1.0.3.tar.gz
Windows binaries: r-devel: stepSplitReg_1.0.3.zip, r-release: stepSplitReg_1.0.3.zip, r-oldrel: stepSplitReg_1.0.3.zip
macOS binaries: r-release (arm64): stepSplitReg_1.0.3.tgz, r-oldrel (arm64): stepSplitReg_1.0.3.tgz, r-release (x86_64): stepSplitReg_1.0.3.tgz, r-oldrel (x86_64): stepSplitReg_1.0.3.tgz
Old sources: stepSplitReg archive

Linking:

Please use the canonical form https://CRAN.R-project.org/package=stepSplitReg to link to this page.