SSGL: Spike-and-Slab Group Lasso for Group-Regularized Generalized Linear Models

Fits group-regularized generalized linear models (GLMs) using the spike-and-slab group lasso (SSGL) prior introduced by Bai et al. (2022) <doi:10.1080/01621459.2020.1765784> and extended to GLMs by Bai (2023) <doi:10.48550/arXiv.2007.07021>. This package supports fitting the SSGL model for the following GLMs with group sparsity: Gaussian linear regression, binary logistic regression, Poisson regression, negative binomial regression, and gamma regression. Stand-alone functions for group-regularized negative binomial regression and group-regularized gamma regression are also available, with the option of employing the group lasso penalty of Yuan and Lin (2006) <doi:10.1111/j.1467-9868.2005.00532.x>, the group minimax concave penalty (MCP) of Breheny and Huang <doi:10.1007/s11222-013-9424-2>, or the group smoothly clipped absolute deviation (SCAD) penalty of Breheny and Huang (2015) <doi:10.1007/s11222-013-9424-2>.

Version: 1.0
Depends: R (≥ 3.6.0)
Imports: stats, MASS, pracma, grpreg
Published: 2023-06-27
DOI: 10.32614/CRAN.package.SSGL
Author: Ray Bai
Maintainer: Ray Bai <raybaistat at>
License: GPL-3
NeedsCompilation: yes
CRAN checks: SSGL results


Reference manual: SSGL.pdf


Package source: SSGL_1.0.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): SSGL_1.0.tgz, r-oldrel (arm64): SSGL_1.0.tgz, r-release (x86_64): SSGL_1.0.tgz, r-oldrel (x86_64): SSGL_1.0.tgz


Please use the canonical form to link to this page.