On 29 Aug 2003 at 20:19, Roger Koenker wrote:

> On Fri, 29 Aug 2003, kjetil brinchmann halvorsen wrote:
> 
> > But is it worth it to modify Kolmogorov-Smirnof fot estimated
> > parameters? It has very low power anyhow. If the null hypothesis is
> > "exponential distributio" (which is a scale family), what about using
> > the quantile transformation twice
> >
> > new <- qnorm(pexp(old))
> 
> And if old is exponential, but not standard exponential?


But the shapiro-wilk test is scale invariant, and the exponential 
family is a scale family, so we can standardize old first without 
destroying the validity of the shapiro-wilk test?

Kjetil Halvorsen


> 
> url:  www.econ.uiuc.edu/~roger/my.html        Roger Koenker
> email [EMAIL PROTECTED]                       Department of Economics
> vox:  217-333-4558                            University of Illinois
> fax:          217-244-6678                            Champaign, IL 61820
> 
>

______________________________________________
[EMAIL PROTECTED] mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help

Reply via email to