[R] (Cross-)validating GLM including factors

[Bert Gunter]

This is not an r-help issue. Post on a statistics list like
stats.stackexchange.com instead for a variety of opinions.*

Cheers,
Bert

*Which will probably be useless given your paucity of data. But that's
just *my* useless opinion.

Bert Gunter
Genentech Nonclinical Biostatistics
(650) 467-7374

"Data is not information. Information is not knowledge. And knowledge
is certainly not wisdom."
Clifford Stoll




On Mon, Feb 2, 2015 at 6:36 AM, Roland Pape
<roland.pape at uni-oldenburg.de> wrote:
> Dear list,
>
> I would like to validate various GLMs, all of them containing (among others) several factors as predictors. I thought about using cv.glm from the boot package, but necessarily got the error "factor xy has new level z". Is there any function to easily cross validate LMs or GLMs containing factors that I have missed, or any other work around?
> - Having in mind that using cross validation on a small data set is not the best solution (I have 50-600 samples, but also three factors with up to 15 levels): Are there any other approaches?
>
> Any help is greatly appreciated!
>
> Roland
>
>         [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.