pairwise.perm.t.test {RVAideMemoire}

Pairwise permutation t tests

Description

Performs pairwise comparisons between group levels with corrections for multiple testing.

Usage

pairwise.perm.t.test(resp, fact, p.method = "fdr", paired = FALSE,
  alternative = c("two.sided","less", "greater"), nperm = 999,
  progress = TRUE)

Arguments

resp

response vector.

fact

grouping factor.

p.method

method for p-values correction. See help of p.adjust.

paired

a logical indicating whether you want paired (permutation) t-tests.

alternative

a character string specifying the alternative hypothesis, must be one of "two.sided" (default), "greater" or "less".

nperm

number of permutations.

progress

logical indicating if the progress bar should be displayed.

Details

The function deals with the limitted floating point precision, which can bias calculation of p-values based on a discrete test statistic distribution.

Value

method

a character string indicating what type of t-tests were performed.

data.name

a character string giving the name(s) of the data.

p.value

table of results.

p.adjust.method

method for p-values correction.

permutations

number of permutations.

Author(s)

Maxime HERVE <[e-mail]>

See Also

pairwise.t.test

Examples

set.seed(1203)
response <- c(rnorm(5),rpois(5,0.5),rnorm(5,2,1))
fact <- gl(3,5,labels=LETTERS[1:3])

# Not enough permutations here but it runs faster

# permutation ANOVA
perm.anova(response~fact,nperm=49)

# Pairwise comparisons
pairwise.perm.t.test(response,fact,nperm=49)