perm.t.test: Permutation Student's t-test

Description

Performs a permutation Student's t-test.

Usage

perm.t.test(x, ...)
# S3 method for default
perm.t.test(x, y, paired = FALSE, ...)
# S3 method for formula
perm.t.test(formula, data, alternative = c("two.sided", "less", "greater"),
  paired = FALSE, nperm = 999, progress = TRUE, ...)

Arguments

a numeric vector of data values.

paired

a logical indicating whether you want a paired t-test.

formula

a formula of the form a ~ b where a gives the data values and b a factor with 2 levels giving the corresponding groups.

data

an optional data frame containing the variables in the formula formula. By default the variables are taken from environment(formula).

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.

…

further arguments to be passed to or from other methods.

Value

statistic

test statistics of the parametric test.

permutations

number of permutations.

p.value

p-value of the permutation test.

estimate

the estimated mean or difference in means depending on whether it was a paired or not paired test.

alternative

a character string describing the alternative hypothesis.

method

a character string indicating what type of t-test was performed.

data.name

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

null.value

the specified hypothesized value of the mean difference, always 0.

Details

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

Examples

Run this code

# NOT RUN {
response <- c(rnorm(5),rnorm(5,2,1))
fact <- gl(2,5,labels=LETTERS[1:2])

# Not enough permutations here but faster to run

# Unpaired test
perm.t.test(response~fact,nperm=49)

# Paired test
perm.t.test(response~fact,paired=TRUE,nperm=49)
# }