Dear S-plussers
After some time and frustrations, I now succeeded in making CVprobs work.
Excuses for any troubles that may have caused you.
The remaining question of the first email may be a non-Splus question:
I am still not sure about the best way of testing the fit of my cross-validated
predictions to my observed values. There is a lot of zeros in data and the
residuals do not seem to be normally distributed. I consider using a rank
correlation test (spearman or kendall), and it does seem to make sense. Is there
a better way?
Regards and happy christmas
Rasmus
Rasmus Ejrnæs
Ph.D. in Plant Ecology
Department of Landscape Ecology
National Environmental Research Institute
> Grenaavej 12, Dk-8410 Ronde, Denmark
tel: +45 8920 1705
fax: +45 8920 1515
-----------------------------------------------------------------------
This message was distributed by s-news@wubios.wustl.edu. To unsubscribe
send e-mail to s-news-request@wubios.wustl.edu with the BODY of the
message: unsubscribe s-news
|