MKinfer (version 1.2)

p2ses: Compute SES from p value.

Description

The function computes the SES (standardized effect size) from the p value for permutation/randomisation tests as proposed by Botta-Dukat (2018).

Usage

p2ses(p, alternative = c("two.sided", "less", "greater"))

Value

SES

Arguments

p

numeric vector of p values.

alternative

a character string specifying the alternative hypothesis, must be one of "two.sided" (default), "greater" or "less". You can specify just the initial letter.

Author

Matthias Kohl

Details

The function uses the probit transformation (qnorm) to compute an alternative SES based on p values from a permutation/randomization test as proposed by Botta-Dukat (2018) for skewed distributions.

References

Botta-Dukat, Z (2018). Cautionary note on calculating standardized effect size (SES) in randomization test. Community Ecology 19(1), 77-83.

Examples

## symmetric case
x <- rnorm(100)
res <- perm.t.test(x)
p2ses(res$p.value)
abs(res$statistic)

## skewed case
x <- rgamma(100, shape = 5)
res <- perm.t.test(x, mu = 5)
p2ses(res$p.value)
abs(res$statistic)