SMLE: Joint Feature Screening via Sparse MLE

Feature screening is a powerful tool in processing ultrahigh dimensional data. It attempts to screen out most irrelevant features in preparation for a more elaborate analysis. Xu and Chen (2014)<doi:10.1080/01621459.2013.879531> proposed an effective screening method SMLE, which naturally incorporates the joint effects among features in the screening process. This package provides an efficient implementation of SMLE-screening for high-dimensional linear, logistic, and Poisson models. The package also provides a function for conducting accurate post-screening feature selection based on an iterative hard-thresholding procedure and a user-specified selection criterion.

Version:	2.1-1
Depends:	R (≥ 4.0.0)
Imports:	glmnet, matrixcalc, mvnfast
Suggests:	testthat (≥ 3.0.0)
Published:	2024-02-12
DOI:	10.32614/CRAN.package.SMLE
Author:	Qianxiang Zang [aut, cre], Chen Xu [aut], Kelly Burkett [aut],
Maintainer:	Qianxiang Zang <qzang023 at uottawa.ca>
License:	GPL-3
NeedsCompilation:	no
Citation:	SMLE citation info
CRAN checks:	SMLE results

Documentation:

Reference manual:

SMLE.pdf

Downloads:

Package source:	SMLE_2.1-1.tar.gz
Windows binaries:	r-devel: SMLE_2.1-1.zip, r-release: SMLE_2.1-1.zip, r-oldrel: SMLE_2.1-1.zip
macOS binaries:	r-release (arm64): SMLE_2.1-1.tgz, r-oldrel (arm64): SMLE_2.1-1.tgz, r-release (x86_64): SMLE_2.1-1.tgz, r-oldrel (x86_64): SMLE_2.1-1.tgz
Old sources:	SMLE archive

Linking:

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