[R-sig-eco] glm-model evaluation

[David Hewitt]

> I've found the package dRedging to be useful for quickly comparing AIC 
> values between all of the models in your workspace. However, I haven't 
> looked at it in too much detail, as I have to use an "n-effective" term 
> instead of the more standard n with my avian nest survival models (a 
> form of binomial glm). So, I just use dRedging to get a rough idea of 
> how the model suite is stacking up, before focusing in on the 
> competitive models.
> 
> The package doesn't seem to be on CRAN, it can be found at:
> http://www.zbs.bialowieza.pl/users/kamil/r/
> 
> If others find problems with it, please share this information.
> 

Jessi,

This goes off-topic a bit, but have you considered using MARK and RMark to
fit nest survival models? If you use RMark, the final returned list includes
a B&A (2002)-style model selection table.

RMark is also not on CRAN, but can be obtained through phidot
(www.phidot.org) under the local MARK software page.

Dave



-----
David Hewitt
Research Fishery Biologist
USGS Klamath Falls Field Station (USA)
-- 
View this message in context: http://www.nabble.com/glm-model-evaluation-tp17525503p17548665.html
Sent from the r-sig-ecology mailing list archive at Nabble.com.