agricolae (version 1.2-6)

kruskal: Kruskal Wallis test and multiple comparison of treatments.

Description

It makes the multiple comparison with Kruskal-Wallis. The parameters by default are alpha = 0.05.

Usage

kruskal(y, trt, alpha = 0.05, p.adj=c("none","holm","hommel", 
"hochberg", "bonferroni", "BH", "BY", "fdr"), group=TRUE, main = NULL,console=FALSE)

Arguments

y

response

trt

treatment

alpha

level signification

p.adj

Method for adjusting p values (see p.adjust)

group

TRUE or FALSE

main

Title

console

logical, print output

Value

y

vector numeric

trt

vector alphanumeric

alpha

level significant

p.adj

text, see p.adjust

group

Logic

main

Title

Details

For equal or different repetition. The post hoc test is using the criterium Fisher's least significant difference. p.adj = "holm", "hommel", "hochberg", "bonferroni", "BH", "BY", "fdr". See p.adjust() p-adj = "none" is t-student. p-adj = "hommel" is not applied in this test.

References

Practical Nonparametrics Statistics. W.J. Conover, 1999

See Also

friedman, durbin.test

Examples

# NOT RUN {
library(agricolae)
data(corn)
str(corn)
comparison<-with(corn,kruskal(observation,method,group=TRUE, main="corn"))
comparison<-with(corn,kruskal(observation,method,p.adj="bon",group=FALSE, main="corn"))
# }