kko: Kernel Knockoffs Selection for Nonparametric Additive Models

A variable selection procedure, dubbed KKO, for nonparametric additive model with finite-sample false discovery rate control guarantee. The method integrates three key components: knockoffs, subsampling for stability, and random feature mapping for nonparametric function approximation. For more information, see the accompanying paper: Dai, X., Lyu, X., & Li, L. (2021). “Kernel Knockoffs Selection for Nonparametric Additive Models”. arXiv preprint <arXiv:2105.11659>.

Version: 1.0.1
Depends: R (≥ 3.6.3)
Imports: grpreg, knockoff, doParallel, parallel, foreach, ExtDist
Suggests: knitr, rmarkdown, ggplot2
Published: 2022-02-01
Author: Xiaowu Dai [aut], Xiang Lyu [aut, cre], Lexin Li [aut]
Maintainer: Xiang Lyu <xianglyu at berkeley.edu>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: no
CRAN checks: kko results

Documentation:

Reference manual: kko.pdf
Vignettes: Vignette of R package kko

Downloads:

Package source: kko_1.0.1.tar.gz
Windows binaries: r-devel: kko_1.0.1.zip, r-release: kko_1.0.1.zip, r-oldrel: kko_1.0.1.zip
macOS binaries: r-release (arm64): kko_1.0.1.tgz, r-oldrel (arm64): kko_1.0.1.tgz, r-release (x86_64): kko_1.0.1.tgz

Linking:

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