reject_set: Finds the rejection set in a multiple testing problem

In NPMLEmix: Two-Groups Mixture Model with Covariates

Description

This function accepts a vector of local false discovery rates from a family of hypotheses and a level parameter, to compute the rejection set.

Usage

reject_set(locfdr, level = 0.1)

Arguments

locfdr	The vector of local false discovery rates (actual or estimated) corresponding to a family of hypotheses.
level	The level at which the false discovery rate is to be controlled. Should ideally be a scalar in [0,1].

Details

The problem of optimal inference in multiple hypotheses testing has been widely studied in literature. In particular, this function adopts the framework and algorithm proposed in Basu et al. See References.

Value

A vector of 1s and 0s with 1s indicating the hypotheses which are to be rejected.

References

Basu, P., Cai, T.T., Das, K. and Sun, W., 2018. Weighted false discovery rate control in large-scale multiple testing. Journal of the American Statistical Association, 113(523), pp.1172-1183.

Deb, N., Saha, S., Guntuboyina, A. and Sen, B., 2018. Two-component Mixture Model in the Presence of Covariates. arXiv preprint arXiv:1810.07897.

Examples

x=cbind(runif(1000),runif(1000))
n=1000
atoms=c(-2,0,2)
probs=c(0.48,0.04,0.48)
variances=c(1,16,1)
sx=c(-3,1.5,1.5)
stdata=makedata(n,x,sx,atoms,probs,variances)
### Obtain the rejection set ###
reject=reject_set(stdata$lo)

NPMLEmix documentation built on Dec. 6, 2020, 9:06 a.m.