knockoff.threshold

Computes the threshold for the knockoff filter.

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.

Matteo Sesia

knockoff

The Knockoff Filter for Controlled Variable Selection

Rina Foygel Barber

Emmanuel Candes

Lucas Janson

Evan Patterson

knockoff.threshold function

<dl><dt>W</dt>
<dd>the test statistics</dd>
<dt>fdr</dt>
<dd>target false discovery rate (default: 0.1)</dd>
<dt>offset</dt>
<dd>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.</dd></dl>

Arguments

Threshold for the knockoff filter — knockoff.threshold

<dl>

<dt>W</dt>
<dd>the test statistics</dd>


<dt>fdr</dt>
<dd>target false discovery rate (default: 0.1)</dd>


<dt>offset</dt>
<dd>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.</dd>

</dl>

knockoff.threshold: Threshold for the knockoff filter

Description

Usage

Value

Arguments