pcLasso v1.1

Monthly downloads

by Rob Tibshirani View Source

Principal Components Lasso

A method for fitting the entire regularization path of the principal components lasso for linear and logistic regression models. The algorithm uses cyclic coordinate descent in a path-wise fashion. See URL below for more information on the algorithm. See Tay, K., Friedman, J. ,Tibshirani, R., (2014) 'Principal component-guided sparse regression' <arXiv:1810.04651>.

Readme

Bug fixes:

predict.pcLasso now works when family = “binomial” (previously, the intercept term was being added in an incorrect manner).
Previously, standardize = TRUE scaled the beta coefficients and intercept a0 incorrectly. This has been fixed.
pcLasso now generates lambda values for the objective function RSS/(2n) + penalty, instead of that for RSS/2 + penalty.

Functions in pcLasso

Name	Description
cv.pcLasso	Cross-validation for pcLasso
pcLasso	Fit a model with principal components lasso
plot.cv.pcLasso	Plot the cross-validation curve produced by "cv.pcLasso" object
predict.cv.pcLasso	Make predictions from a "cv.pcLasso" object
predict.pcLasso	Make predictions from a "pcLasso" object
No Results!

Vignettes of pcLasso

Name
pcLasso.Rmd
No Results!

Last month downloads

Details

Type	Package
License	GPL-3
URL	https://arxiv.org/abs/1810.04651
Encoding	UTF-8
LazyData	true
RoxygenNote	6.1.1
VignetteBuilder	knitr
NeedsCompilation	yes
Packaged	2019-02-06 00:11:42 UTC; robtibshirani
Repository	CRAN
Date/Publication	2019-02-06 12:30:03 UTC

suggests	knitr , rmarkdown
imports	svd
Contributors	Robert Tibshirani, Jerome Friedman, Kenneth Tay