BFDR: BFDR computation, one-sided, two-sided and multiple...

In markvdwiel/ShrinkBayes: Bayesian analysis of high-dimensional omics data, either Gaussian or counts

BFDR computation, one-sided, two-sided and multiple comparisons

Description

This function computes Bayesian FDRs from posterior tail probabilities or local fdrs P(H0|Y).

Usage

BFDR(lfdr1,lfdr2=NULL,multcomp=FALSE)

Arguments

lfdr1	Vector or matrix containing tail probabilities for each comparison or parameter
lfdr2	Vector or matrix containing tail probabilities (to the the other side than those in lfdr1) for each comparison or parameter
multcomp	Boolean, TRUE or FALSE indicating whether a multiple comparison is desired

Details

See Ventrucci et al. reference below for interpretation of BFDR, also in comparison with ordinary FDR. Posterior tail probabilities can be computed with the function SummaryWrap

Value

A numerical vector or matrix. A matrix is returned when the input lfdrs are matrices and multcomp=FALSE.

Author(s)

Mark A. van de Wiel

References

Ventrucci, M, Scott, EM and Cocchi, D (2011). Multiple testing on standardized mortality ratios: a Bayesian hierarchical model for FDR estimation. Biostatistics 12, 51-67.

Van de Wiel MA, Leday GGR, Pardo L, Rue H, Van der Vaart AW, Van Wieringen WN (2012). Bayesian analysis of RNA sequencing data by estimating multiple shrinkage priors. Biostatistics.

See Also

SummaryWrap

Examples

#See ShrinkSeq, ShrinkGauss and CombinePosteriors

markvdwiel/ShrinkBayes documentation built on March 27, 2022, 7:47 p.m.