reglogit: Simulation-Based Regularized Logistic Regression

Regularized (polychotomous) logistic regression by Gibbs sampling. The package implements subtly different MCMC schemes with varying efficiency depending on the data type (binary v. binomial, say) and the desired estimator (regularized maximum likelihood, or Bayesian maximum a posteriori/posterior mean, etc.) through a unified interface.

Version: 1.2-4
Depends: R (≥ 2.14.0), methods, mvtnorm, boot, Matrix
Suggests: plgp
Published: 2015-06-22
Author: Robert B. Gramacy
Maintainer: Robert B. Gramacy <rbgramacy at>
License: LGPL-2 | LGPL-2.1 | LGPL-3 [expanded from: LGPL]
NeedsCompilation: yes
Materials: ChangeLog
CRAN checks: reglogit results


Reference manual: reglogit.pdf
Package source: reglogit_1.2-4.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
OS X Snow Leopard binaries: r-release: reglogit_1.2-4.tgz, r-oldrel: reglogit_1.2-2.tgz
OS X Mavericks binaries: r-release: reglogit_1.2-4.tgz
Old sources: reglogit archive