knockoff: The Knockoff Filter for Controlled Variable Selection

The knockoff filter is a general procedure for controlling the false discovery rate (FDR) when performing variable selection. For more information, see the website below and the accompanying paper: Candes et al., "Panning for Gold: Model-X Knockoffs for High-dimensional Controlled Variable Selection", 2016, <arXiv:1610.02351>.

Version: 0.3.2
Depends: methods, stats
Imports: Rdsdp, Matrix, corpcor, glmnet, RSpectra, gtools, utils
Suggests: knitr, testthat, rmarkdown, lars, ranger, stabs, flare, doMC, parallel
Published: 2018-09-16
Author: Rina Foygel Barber [ctb] (Development of the original Fixed-X Knockoffs), Emmanuel Candes [ctb] (Development of Model-X Knockoffs and original Fixed-X Knockoffs), Lucas Janson [ctb] (Development of Model-X Knockoffs), Evan Patterson [aut] (Original R package for the original Fixed-X Knockoffs), Matteo Sesia [aut, cre] (R package for Model-X Knockoffs)
Maintainer: Matteo Sesia <msesia at>
License: GPL-3
NeedsCompilation: no
Materials: NEWS
CRAN checks: knockoff results


Reference manual: knockoff.pdf
Vignettes: Advanced Usage of the Knockoff Filter for R
Controlled variable Selection with Fixed-X Knockoffs
Analysis of HIV Drug Resistance Data
Controlled variable Selection with Model-X knockoffs
Package source: knockoff_0.3.2.tar.gz
Windows binaries: r-prerelease:, r-release:, r-oldrel:
macOS binaries: r-prerelease: knockoff_0.3.2.tgz, r-release: knockoff_0.3.2.tgz, r-oldrel: knockoff_0.3.2.tgz
Old sources: knockoff archive

Reverse dependencies:

Reverse imports: KOBT
Reverse suggests: CBDA


Please use the canonical form to link to this page.