sis: Variable Screening before Selection for Continuous Response

Description Usage Arguments Details Value References

View source: R/sis.R

Description

When the response is continuous, this function screens the variables before computing their statistics to reduce computing time, especially when p is large.

Usage

1
sis(Xaug, y, N = nrow(Xaug), knot = 10)

Arguments

Xaug

augmented design matrix combining original predictors and knockoff variables

y

response vector, or a survival object with two columns

N

number of variables left after screening (default: sample size)

knot

parameter in screening process

Details

Sure Independence Screening (SIS) method is used in this function. The screening process would accelerate computing but not necessarily improve power as true signals might be removed by this process. Our experiment indicates that the power would remain almost the same.

Value

a binary 2p by 1 vector for screening results. 1 means selected by the screening and 0 otherwise.

References

Jianqing Fan and Jinchi Lv (2008) Sure Independence Screening for Ultrahigh Dimensional Feature Space (with discussion). Journal of Royal Statistical Society B, 70, 849-911.


hanfu-bios/varsel documentation built on March 19, 2018, 10:08 a.m.