[R] effect sizes for Wilcoxon tests

[Claus Atzenbeck]

On Tue, 15 Nov 2005, Thomas Lumley wrote:

> I think you have misinterpreted the direction of Peter's scepticism.
> The question is whether an effect size defined this way means anything
> useful. For example, even if your data are Normally distributed with
> equal variance this definition will not agree with the definition
> based on the mean. This is only the start of the potential problems,
> especially if the distributions do not have the same shape.

I see the point. The book that I use (it is a kind of practical guide)
calculates the effect sizes of Mann-Whitney tests  and compares it to
Cohen's benchmarks (small effect: r=.10 -- medium effect: r=.30 -- large
effect: r=.50). This was also my plan. However, as far as I understand
you and Peter, the formula is not appropriate for comparison with
Cohen's benchmarks?

> > However, how do I get Z from a Wilcoxon test in R?
>
> wtest <- wilcox.test(y~group,data=d, alternative="greater")
> qnorm(wtest$p.value)

Thanks, also to Peter.

Claus