multtest.gp {RVAideMemoire}

Univariate comparison of groups for multiple variables

Description

Performs group comparisons for multiple variables using parametric, permutational or rank tests, and corrects p-values. Gives also group means and standards errors for each variable.

Usage

multtest.gp(tab, fac, test = c("param", "perm", "rank"),
  transform = c("none", "sqrt", "4rt", "log"), add = 0, p.method = "fdr",
  ordered = TRUE, ...)

## S3 method for class 'multtest.gp'
plot(x, signif = FALSE, alpha = 0.05,
  vars = NULL, xlab = "Group", ylab = "Mean (+/- SE) value",
  titles = NULL, groups = NULL, ...)

Arguments

tab

data frame containing response variables.

fac

factor defining groups to compare.

test

type of test to use: parametric (default), permutational (non parametric) or rank-based (non parametric). See Details.

transform

transformation to apply to response variables before testing (none by default; "4rt" is fourth-root). Only used for parametric and permutational tests.

add

value to add to response variables before a log-transformation.

p.method

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

ordered

logical indicating if variables should be ordered based on p-values.

x

object returned from multtest.gp.

signif

logical indicating if only variables with significant P-value should be plotted.

alpha

significance threshold.

vars

numeric vector giving variables to plot (rows of x). Default to all, which can lead to errors if too many variables.

xlab

legend of the x axis.

ylab

legend of the y axis

titles

titles of the graphs (name of the variables by default).

groups

names of the bars (levels of fac by default).

...

additional arguments to testing functions in multtest.gp (especially for var.equal in t.test and nperm in perm.anova and perm.t.test) and to barplot in plot.

Details

In case of parametric tests, t-tests or ANOVAs are used depending on the number of groups (2 or more, respectively). In case of permutational tests: permutational t-tests or permutational ANOVAs. In case of rank-based tests: Mann-Whitney-Wilcoxon or Kruskal-Wallis tests.

Author(s)

Maxime HERVE <[e-mail]>

See Also

perm.anova, perm.t.test

Examples

data(iris)
mult <- multtest.gp(iris[,1:4],iris$Species)
plot(mult)