plot.nparttestpaired: Visualizing the result of 'npar.t.test.paired'

In nparcomp: Multiple Comparisons and Simultaneous Confidence Intervals

Description

This function takes an object of class "nparttestpaired" and creates a plot of the confidence intervals for the estimated effect resulting from the studentized permutation test and the Brunner-Munzel test.

Usage

## S3 method for class 'nparttestpaired'
plot(x,...)

Arguments

x	x An object of class "nparttestpaired", i.e. the result when applying npar.t.test.paired to a dataset. Otherwise an error will occur.
...	... Arguments to be passed to methods.

Details

It is not possible to change any parameter set in the npar.t.test.paired-statement.

Since plot.nparttestpaired is a S3 method it suffices to use plot(x) as long as x is of class "nparttestpaired". It will be interpreted as plot.nparttestpaired(x).

Value

plot.npar.t.test returns a graph that contains a confidence interval for the estimated effect of the nonparametric studentized permutation test as well as. It just visualizes the result of the npar.t.test.paired-statement.

Note

It is possible to create a graphical result of the nonparametric studentized permutation test directly by setting plot.simci=TRUE in the npar.t.test.paired-statement.

Author(s)

Frank Konietschke

References

Munzel, U., Brunner, E. (2002). An Exact Paired Rank Test. Biometrical Journal 44, 584-593.

Konietschke, F., Pauly, M. (2012). A Studentized Permutation Test for the Nonparametric Behrens-Fisher Problem in Paired Data. Electronic Journal of Statistic, Vol 6, 1358-1372.

See Also

For further information on the usage of npar.t.test.paired, see npar.t.test.paired.

Examples

## Not run: 
data(PGI)
a<-npar.t.test.paired(PGIscore~timepoint, data = PGI, 
               alternative = "two.sided", info=TRUE, plot.simci=FALSE)
plot(a)

## End(Not run)

nparcomp documentation built on June 25, 2019, 5:02 p.m.