Learn R Programming

knockoff (version 0.3.6)

The Knockoff Filter for Controlled Variable Selection

Description

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", J. R. Statist. Soc. B (2018) 80, 3, pp. 551-577.

Copy Link

Version

Install

install.packages('knockoff')

Monthly Downloads

399

Version

0.3.6

License

GPL-3

Maintainer

Matteo Sesia

Last Published

August 15th, 2022

Functions in knockoff (0.3.6)

create.solve_equi

Optimization for equi-correlated fixed-X and Gaussian knockoffs
create_equicorrelated

Create equicorrelated fixed-X knockoffs.
create.solve_asdp

Relaxed optimization for fixed-X and Gaussian knockoffs
create.second_order

Second-order Gaussian knockoffs
create.fixed

Fixed-X knockoffs
create.gaussian

Model-X Gaussian knockoffs
decompose

Compute the SVD of X and construct an orthogonal matrix U_perp such that U_perp * U = 0.
divide.sdp

Approximate a covariance matrix by a block diagonal matrix with blocks of approximately equal size using Ward's method for hierarchical clustering
create_sdp

Create SDP fixed-X knockoffs.
create.solve_sdp

Optimization for fixed-X and Gaussian knockoffs
fs

Forward selection
merge.clusters

Merge consecutive clusters of correlated variables while ensuring that no cluster has size larger than max.size
print.knockoff.result

Print results for the knockoff filter
lasso_max_lambda

Maximum lambda in lasso model
stability_selection_importance

Stability selection
knockoff.threshold

Threshold for the knockoff filter
knockoff.filter

The Knockoff Filter
stat.sqrt_lasso

Importance statistics based on the square-root lasso
stat.random_forest

Importance statistics based on random forests
stat.lasso_coefdiff

Importance statistics based the lasso with cross-validation
stat.lasso_coefdiff_bin

Importance statistics based on regularized logistic regression with cross-validation
stat.lasso_lambdadiff_bin

Importance statistics based on regularized logistic regression
stat.lasso_lambdadiff

Importance statistics based on the lasso
knockoff

knockoff: A package for controlled variable selection
stat.glmnet_coefdiff

Importance statistics based on a GLM with cross-validation
stat.forward_selection

Importance statistics based on forward selection
verify_stat_depends

Verify dependencies for chosen statistics
stat.lasso_lambdasmax_bin

Penalized logistic regression statistics for knockoff
stat.lasso_lambdasmax

Penalized linear regression statistics for knockoff
stat.glmnet_lambdasmax

GLM statistics for knockoff
stat.glmnet_lambdadiff

Importance statistics based on a GLM
create.vectorize_matrix

Vectorize a matrix into the SCS format
stat.stability_selection

Importance statistics based on stability selection