Learn R Programming

SplitKnockoff (version 2.1)

Split Knockoffs for Structural Sparsity

Description

Split Knockoff is a data adaptive variable selection framework for controlling the (directional) false discovery rate (FDR) in structural sparsity, where variable selection on linear transformation of parameters is of concern. This proposed scheme relaxes the linear subspace constraint to its neighborhood, often known as variable splitting in optimization. Simulation experiments can be reproduced following the Vignette. 'Split Knockoffs' is first defined in Cao et al. (2021) .

Copy Link

Version

Install

install.packages('SplitKnockoff')

Monthly Downloads

210

Version

2.1

License

MIT + file LICENSE

Maintainer

Yuxuan Chen

Last Published

October 14th, 2024

Functions in SplitKnockoff (2.1)

sk.create

generate split knockoff copies
select

split knockoff selector given W statistics
hittingpoint

hitting point calculator on a given path
sk.W_path

W statistics generator based on the beta(lambda) from a split LASSO path
canonicalSVD

singular value decomposition
cv_all

calculate the CV optimal beta
cv_screen

calculate the CV optimal beta and estimated support set
sk.W_fixed

W statistics generator based on a fixed beta(lambda) = hat beta
normc

default normalization function for matrix
sk.decompose

make SVD as well as orthogonal complements
threshold

compute the threshold for variable selection
sk.filter

split Knockoff filter for structural sparsity problem