False discovery rate regression

Tools for FDR problems, including false discovery rate regression. See corresponding paper: "False discovery rate regression: application to neural synchrony detection in primary visual cortex." James G. Scott, Ryan C. Kelly, Matthew A. Smith, Robert E. Kass.

R package for false discovery rate regression (FDRR)

Many approaches for multiple testing begin with the assumption that all tests in a given study should be combined into a global false-discovery-rate analysis. But this may be inappropriate for many of today's large-scale screening problems, where auxiliary information about each test is often available, and where a combined analysis can lead to poorly calibrated error rates within different subsets of the experiment.

This package implements false-discovery-rate regression (FDRR), in which auxiliary covariate information is used to improve power while maintaining control over the global error rate. The method can be motivated by a hierarchical Bayesian model in which covariates are allowed to influence the local false discovery rate (or equivalently, the posterior probability that a given observation is a signal) via a logistic regression.

To install the package in R, first install the devtools package, and then use the commands


The method is described in the paper 'False discovery rate regression: an application to neural synchrony detection in primary visual cortex', available as arXiv:1307.3495 (stat.ME).


Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.


0.1 by James G. Scott, 5 years ago

Browse source code at https://github.com/cran/FDRreg

Authors: James G. Scott , with contributions from Rob Kass and Jesse Windle

Documentation:   PDF Manual  

GPL (>= 3) license

Imports Rcpp, mosaic

Depends on fda, splines

Linking to Rcpp, RcppArmadillo

See at CRAN