NormalTests {compositions}

Compositional Goodness of fit test

Description

Tests for several groups of additive lognormally distributed compositions.

Usage

  acompNormalLocation.test(x, g=NULL, var.equal=FALSE, paired=FALSE, 
                                R=ifelse(var.equal,999,0))
          

Arguments

x

a dataset of compositions (acomp) or a list of such

g

a factor grouping the data, not used if x is a list already. Alternatively, g can be a second compositional data set.

var.equal

a boolean telling wether the variance of the groups should be considered equal

paired

true if a paired test should be performed

R

number of replicates that should be used to compute p-values. 0 means comparing the likelihood statistic with the correponding asymptotic chisq-distribution.

Details

The tests are based on likelihood ratio statistics.

Value

A classical "htest" object

data.name

The name of the dataset as specified

method

a name for the test used

alternative

an empty string

replicates

a dataset of p-value distributions under the Null-Hypothesis got from nonparametric bootstrap

p.value

The p.value computed for this test

Missing Policy

Up to now the tests cannot handle missings.

Note

Do not trust the p-values obtained forcing var.equal=TRUE and R=0. This will include soon equivalent spread tests.

Author(s)

K.Gerald v.d. Boogaart http://www.stat.boogaart.de

References

Aitchison, J. (1986) The Statistical Analysis of Compositional Data Monographs on Statistics and Applied Probability. Chapman & Hall Ltd., London (UK). 416p.

See Also

fitDirichlet,rDirichlet, runif.acomp, rnorm.acomp,

Examples

x <- runif.acomp(100,4)
y <- runif.acomp(100,4)
acompNormalLocation.test(list(x,y))