Median.test: Median test. Multiple comparisons

Description

A nonparametric test for several independent samples. The median test is designed to examine whether several samples came from populations having the same median.

Usage

Median.test(y,trt,alpha=0.05,correct=TRUE,simulate.p.value = FALSE, group = TRUE, 
main = NULL,console=TRUE)

Value

statistics: Statistics of the model
parameters: Design parameters
medians: Statistical summary of the study variable
comparison: Comparison between treatments
groups: Formation of treatment groups

Arguments

y: Variable response
trt: Treatments
alpha: error type I
correct: a logical indicating whether to apply continuity correction when computing the test statistic for 2 groups. The correction will not be bigger than the differences themselves. No correction is done if simulate.p.value = TRUE.
simulate.p.value: a logical indicating whether to compute p-values by Monte Carlo simulation
group: TRUE or FALSE
main: Title
console: logical, print output

Author

Felipe de Mendiburu

Details

The data consist of k samples of possibly unequal sample size.
Greater: is the number of values that exceed the median of all data and
LessEqual: is the number less than or equal to the median of all data.

References

Practical Nonparametrics Statistics. W.J. Conover, 1999

Examples

Run this code

library(agricolae)
# example 1
data(corn)
out<-with(corn,Median.test(observation,method,console=FALSE))
z<-bar.err(out$medians,variation = "range",ylim=c(0,120),
           space=2,border=4,col=3,density=10,angle=45)
# example 2
out<-with(corn,Median.test(observation,method,console=FALSE,group=FALSE))
print(out$comparison)

Run the code above in your browser using DataLab