RXshrink: Maximum Likelihood Shrinkage using Generalized Ridge or Least Angle Regression Methods

Functions are provided to calculate and display ridge TRACEs for various shrinkage Paths. They determine the m-Extent of shrinkage most likely, under Normal-theory, to produce optimally biased estimates of regression beta-coefficients with minimum MSE Risk. The new unr.ridge() function implements the "Unrestricted Path" introduced in "Ridge TRACE Diagnostics" <arXiv:2005.14291>. This Path appears more efficient than the Paths used by the qm.ridge(), aug.lars() and uc.lars() functions. In-Sample predictions can be made using RXpredict() for all five types of RXshrink linear model TRACE diagnostics. New functions MLboot(), MLcalc(), MLhist() and MLtrue() provide insights into the true bias and MSE risk characteristics of non-linear Shrinkage estimators. The correct.signs() function provides estimates with "correct" numerical signs when ill-conditioned (nearly multicollinear) models yield OLS estimates that disagree with the signs of the observed correlations between the y-outcome and the selected x-predictor variables.

Version: 1.4
Depends: R (≥ 3.5.0), lars
Published: 2020-06-26
Author: Bob Obenchain
Maintainer: Bob Obenchain <wizbob at att.net>
License: GPL-2
URL: https://www.R-project.org , http://localcontrolstatistics.org , http://arxiv.org/abs/2005.14291
NeedsCompilation: no
In views: MachineLearning
CRAN checks: RXshrink results


Reference manual: RXshrink.pdf
Package source: RXshrink_1.4.tar.gz
Windows binaries: r-devel: RXshrink_1.4.zip, r-release: RXshrink_1.4.zip, r-oldrel: RXshrink_1.4.zip
macOS binaries: r-release: RXshrink_1.4.tgz, r-oldrel: RXshrink_1.4.tgz
Old sources: RXshrink archive


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