emBayes: Robust Bayesian Variable Selection via Expectation-Maximization

Variable selection methods have been extensively developed for analyzing high-dimensional omics data within both the frequentist and Bayesian frameworks. This package implemented the spike-and-slab quantile LASSO which has been developed along the line of Bayesian hierarchical model but deeply rooted in the frequentist regularization methods by utilizing the Expectation–Maximization (EM) algorithm. Therefore, the proposed method borrows strength from both the frequentist and Bayesian frameworks while overcoming their respective limitations. The spike-and-slab quantile LASSO can handle data irregularity in terms of skewness and outliers in the disease trait, compared to its nonrobust alternative, the spike-and-slab LASSO, which has also been implemented in the package. The core module of this package is developed in 'C++'.

Version:	0.1.5
Depends:	R (≥ 4.2.0)
Imports:	Rcpp, glmnet
LinkingTo:	Rcpp, RcppArmadillo
Published:	2024-03-29
Author:	Yuwen Liu [aut, cre], Cen Wu [aut]
Maintainer:	Yuwen Liu <yuwen at ksu.edu>
License:	GPL-2
NeedsCompilation:	yes
CRAN checks:	emBayes results

Documentation:

Reference manual:

emBayes.pdf

Downloads:

Package source:	emBayes_0.1.5.tar.gz
Windows binaries:	r-devel: emBayes_0.1.5.zip, r-release: emBayes_0.1.5.zip, r-oldrel: emBayes_0.1.5.zip
macOS binaries:	r-release (arm64): emBayes_0.1.5.tgz, r-oldrel (arm64): emBayes_0.1.5.tgz, r-release (x86_64): emBayes_0.1.5.tgz, r-oldrel (x86_64): emBayes_0.1.5.tgz
Old sources:	emBayes archive

Linking:

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