CrossScreening (version 0.1.1)

bonferroni.fg: Bonferroni's correction with fixed

Description

Bonferroni's correction with fixed \(\Gamma\)

Usage

bonferroni.fg(d, gamma = 1, mm = c(2, 2, 2), two.sided = TRUE)

Arguments

d

a matrix of treatment-minus-control differences.

gamma

sensitivity parameter (maximum odds different from a randomized experiment).

mm

test statistic, either a vector of length 3 or a matrix of three rows where each column corresponds to a U-statistic. Default is the (approximate) Wilcoxon's signed rank test.

two.sided

whether a two-sided test should be used. If FALSE, test the one-sided alternative that the center of d is positive.

Value

a vector of sensitivity values for each column of d

Details

If mm is a matrix, this function computes a one-sided or two-sided p-value with each statistic (i.e. there is a p-value for every column of d and every column of $mm$), then does a Bonferroni correction over all the p-values.