histf1: Histogram estimator of p-value density evaluated at 1

Description

Histogram estimator of p-value density evaluated at 1. See references.

Usage

histf1(p,max.bins=20,bin.method=c("max","nmse","bootstrap",
      "Sturges","Scott","FD"),discrete=FALSE,seq.perm=FALSE,
      nboots=200,rightBoundary=FALSE,plotit=FALSE,perm.n,perm.h,...)

Arguments

Vector of p-values

max.bins

maximum number of bins

bin.method

binning method

discrete

Whether p-values are discrete

seq.perm

Whether p-values come from sequential permutation tests

nboots

bootstrap sample size

rightBoundary

Logical; if TRUE, then the tail mean is computed from the right boundary of the chosen bin.

plotit

Whether to plot the histogram

perm.n

n for sequential permutation tests

perm.h

h for sequential permutation tests

...

Other arguments passed to hist

Value

A numeric scalar value of estimated p-value density at 1.

References

Nettleton, Hwang, Caldo, Wise. 2006. Estimating the number of true null hypotheses from a histogram of $p$ values. Journal of Agricultural, Biological, and Environmental Statistics. 11. 337-356. Bancroft and Nettleton. 2009. Estimation of False Discovery Rate Using Permutation P-values with Different Discrete Null Distributions. Iowa State University Department of Statistics Preprint Series, #2009-05. Bancroft and Nettleton. 2009. Computationally Efficient Estimation of False Discovery Rate Using Sequential Permutation P-values. Iowa State University Department of Statistics Preprint Series, #2009-04. Liang and Nettleton. 2012. Adaptive and dynamic adaptive procedures for false discovery rate control and estimation, Journal of the Royal Statistical Society, Series B. 74. 163-182

Examples

Run this code

set.seed(9992722)
histf1(runif(5e5)^1.5) ##  [1] 0.6762