MHTdiscrete (version 1.0.1)

Roth.rej: The number of rejected hypotheses for Roth's step-up FWER controlling procedure.

Description

The function for calculating the number of rejected hypotheses (rejection region) based on original available p-values, all attaianble p-values and the given significant level.

Usage

Roth.rej(p,p.set,alpha)

Arguments

p

numeric vector of p-values (possibly with NAs). Any other R is coerced by as.numeric. Same as in p.adjust.

p.set

a list of numeric vectors, where each vector is the vector of all attainable p-values containing the available p-value for the corresponding hypothesis..

alpha

the given significant level for Roth's procedure, the default value is 0.05.

Value

An integer value of the number of rejected hypotheses.

References

Roth, A. J. (1999). Multiple comparison procedures for discrete test statistics. Journal of statistical planning and inference, 82: 101-117.

Hochberg, Y. (1988). A sharper Bonferroni procedure for multiple tests of significance. Biometrika, 75: 800-803.

Examples

# NOT RUN {
p <- c(pbinom(1,8,0.5),pbinom(1,5,0.75),pbinom(1,6,0.6))
p.set <-list(pbinom(0:8,8,0.5),pbinom(0:5,5,0.75),pbinom(0:6,6,0.6))
Roth.rej(p,p.set,0.05)
# }