rmanova: A heteroscedastic one-way repeated measures ANOVA for trimmed means.

Description

The rmanova function computes a one-way repeated measures ANOVA for the trimmed means. Homoscedasticity assumption not required. Corresponding post hoc tests can be performed using rmmcp.

Usage

rmanova(y, groups, blocks, tr = 0.2, ...)
rmmcp(y, groups, blocks, tr = 0.2, alpha = 0.05, ...)

Value

rmanova an object of class "t1way" containing:

test: value of the test statistic
df1: degrees of freedom
df2: degrees of freedom
p.value: p-value
call: function call

rmmcp returns an object of class "mcp1" containing:

comp: inference for all pairwise comparisons
fnames: names of the factor levels

Arguments

y: a numeric vector of data values (response).
groups: a vector giving the group of the corresponding elements of y.
blocks: a vector giving the block of the corresponding elements of y.
tr: trim level for the mean.
alpha: alpha level for post hoc comparisons.
...: currently ignored.

References

Wilcox, R. (2012). Introduction to Robust Estimation and Hypothesis Testing (3rd ed.). Elsevier.

Examples

Run this code

head(WineTasting)
rmanova(WineTasting$Taste, WineTasting$Wine, WineTasting$Taster)

## post hoc
rmmcp(WineTasting$Taste, WineTasting$Wine, WineTasting$Taster)

head(bush)
require(reshape)
bushLong <- melt(bush, id.var = "participant", variable_name = "food")
rmanova(bushLong$value, bushLong$food, bushLong$participant)

## post hoc
rmmcp(bushLong$value, bushLong$food, bushLong$participant)