Learn R Programming

kko (version 1.0.1)

Kernel Knockoffs Selection for Nonparametric Additive Models

Description

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). <80><9c>Kernel Knockoffs Selection for Nonparametric Additive Models<80><9d>. arXiv preprint .

Copy Link

Version

Install

install.packages('kko')

Monthly Downloads

217

Version

1.0.1

License

GPL (>= 2)

Maintainer

Xiang Lyu

Last Published

February 1st, 2022

Functions in kko (1.0.1)

rk_subsample

compute selection frequency of rk_fit on subsamples
KO_evaluation

evaluate performance of KKO selection
rk_tune

tune random feature number for KKO.
rk_fit

nonparametric additive model seleciton via random kernel
kko

variable selection for additive model via KKO
generate_data

generate response from nonparametric additive model