shrink: Global, Parameterwise, and Joint Post-Estimation Shrinkage

Post-estimation shrinkage of regression coefficients in statistical modeling can be used to correct for the overestimation of regression coefficients caused by variable selection. While global shrinkage modifies all regression coefficients by the same factor, parameterwise shrinkage factors differ between regression coefficients. With highly correlated or semantically related variables, such as several columns of a design matrix describing a nonlinear effect, parameterwise shrinkage factors are not interpretable and a compromise between global and parameterwise shrinkage, termed 'joint shrinkage', is a useful extension. A computational shortcut to resampling-based shrinkage factor estimation based on DFBETA residuals is applied. Global, parameterwise, and joint shrinkage for models fitted by lm, glm, coxph, or mfp is available.

Version: 1.1
Suggests: survival, mfp, rms, MASS
Published: 2013-10-21
Author: Daniela Dunkler, Georg Heinze
Maintainer: Daniela Dunkler <daniela.dunkler at meduniwien.ac.at>
License: GPL-2
NeedsCompilation: no
Citation: shrink citation info
Materials: ChangeLog
CRAN checks: shrink results

Downloads:

Reference manual: shrink.pdf
Package source: shrink_1.1.tar.gz
MacOS X binary: shrink_1.1.tgz
Windows binary: shrink_1.1.zip
Old sources: shrink archive