Select Variables based on knockoff statistics

Select Variables based on knockoff statistics

knockoff.select(Ws, fdr = 0.1, offset = 1)

Arguments

Ws

the test statistics, it is either a nrep by p matrix, or list of length to be nrep, or a vector with length being p.

fdr

target false discovery rate (default: 0.1)

offset

either 0 or 1 (default: 1). The offset used to compute the rejection threshold on the statistics. The value 1 yields a slightly more conservative procedure ("knockoffs+") that controls the FDR according to the usual definition, while an offset of 0 controls a modified FDR.

Value

An object of class "knockoff.select. This object is a list containing at least the following components:

W

computed test statistics

Ws

matrix of computed test statistics

thre

computed selection threshold

index

index of selected variables