[R] G-test

[Laurent Gautier]

Philippe Grosjean wrote:

> > Do you refer to something related to the Getis statistics ? If so,
> you may find helpfull things in the geoR package (which is btw
> described in the exxxxcellent latest R-newsletter).
> I suspect it is rather the G-test, alias "log likelihood ratio test",
> a test similar to Chi-2 but more robust (see: Sokal & Rholf, Biometry,
> 2nd Ed, p. 696)... I am interested too. So, if someone has a
> suggestion? Best regards,Philippe Grosjean
>

....hmmmm....


If I recollect correctly, the VR package offers something called loglm
that could do what you are looking for....




Regards,





Laurent




--
Laurent Gautier                 CBS, Building 208, DTU
PhD. Student                    D-2800 Lyngby,Denmark
tel: +45 45 25 24 85            http://www.cbs.dtu.dk/laurent


-------------- next part --------------
An HTML attachment was scrubbed...
URL: https://stat.ethz.ch/pipermail/r-help/attachments/20010712/e37d2b21/attachment.html