Computes solutions for linear and logistic regression models with a nonconvex penalty (SCOPE) in an efficient path-wise fashion (Stokell, Shah and Tibshirani 2020, <arXiv:2002.12606>). The scaling of the solution paths is selected automatically. Includes functionality for selecting tuning parameter lambda by k-fold cross-validation and early termination based on information criteria. Solutions are computed by cyclical block-coordinate descent, iterating an innovative dynamic programming algorithm to compute exact solutions for each block.
| Version: | 1.0.0 |
| Imports: | Rcpp (≥ 1.0.1), Rdpack |
| LinkingTo: | Rcpp |
| Published: | 2020-03-14 |
| Author: | Benjamin Stokell [aut], Daniel Grose [ctb, cre], Rajen Shah [ctb] |
| Maintainer: | Daniel Grose <dan.grose at lancaster.ac.uk> |
| License: | GPL-2 | GPL-3 [expanded from: GPL (≥ 2)] |
| NeedsCompilation: | yes |
| CRAN checks: | CatReg results |
| Reference manual: | CatReg.pdf |
| Package source: | CatReg_1.0.0.tar.gz |
| Windows binaries: | r-devel: CatReg_1.0.0.zip, r-release: CatReg_1.0.0.zip, r-oldrel: CatReg_1.0.0.zip |
| macOS binaries: | r-release: CatReg_1.0.0.tgz, r-oldrel: CatReg_1.0.0.tgz |
Please use the canonical form https://CRAN.R-project.org/package=CatReg to link to this page.