pwrFDR: FDR Power

This is a package for calculating two differing notions of power, or deriving sample sizes for specified requisite power in multiple testing experiments under a variety of methods for control of the distribution of the False Discovery Proportion (FDP). More specifically, one can choose to control the FDP distribution according to control of its (i) mean, e.g. the usual BH-FDR procedure, or via the probability that it exceeds a given value, delta, via (ii) the Romano procedure, or via (iii) my procedure based upon asymptotic approximation. Likewise, we can think of the power in multiple testing experiments in terms of a summary of the distribution of the True Positive Proportion (TPP). The package will compute power, sample size or any other missing parameter required for power based upon (i) the mean of the TPP which is the average power (ii) the probability that the TPP exceeds a given value, lambda, via my asymptotic approximation procedure. The theoretical results are described in Izmirlian, G. (2020) Stat. and Prob. letters, <doi:10.1016/j.spl.2020.108713>, and an applied paper describing the methodology with a simulation study is in preparation.

Version: 2.8.9
Imports: methods, stats
Published: 2021-05-12
Author: Grant Izmirlian Jr
Maintainer: Grant Izmirlian Jr <izmirlig at>
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
NeedsCompilation: yes
CRAN checks: pwrFDR results


Reference manual: pwrFDR.pdf


Package source: pwrFDR_2.8.9.tar.gz
Windows binaries: r-devel:, r-devel-UCRT:, r-release:, r-oldrel:
macOS binaries: r-release (arm64): pwrFDR_2.8.9.tgz, r-release (x86_64): pwrFDR_2.8.9.tgz, r-oldrel: pwrFDR_2.8.9.tgz
Old sources: pwrFDR archive


Please use the canonical form to link to this page.