[R-sig-ME] using MuMIn with glmmADMB

[Rafael Mares]

Yes, that worked. Thank you very much Ben.

Raff


On 21 April 2012 14:11, Ben Bolker <bbolker at gmail.com> wrote:
> Rafael Mares <raffmares at ...> writes:
>
>> Has anyone tried to use MuMIn along with glmmADMB? I'm trying to use
>> the importance() function from the MuMIn package (version 1.7.7) to
>> the get the sum of AIC weights across models that include a given
>> explanatory variable, within a set of candidate models fitted using
>> glmmADMB (version 0.7).
>>
>> I've used this for models fitted with lme4, and it works like this:
>> importance(c(mod0, mod1, mod2, mod3))
>> where mod[i] is the model name.
>>
>> This doesn't seem to work for models fitted with glmmADMB, as I get:
>> "Error in formula.default(x) : invalid formula"
>
> [snip]
>
>  It seems to work fine if I use list(mod0,mod1), for example:
>
> library(glmmADMB)
> example(glmmadmb)
> bfit1 <- update(bfit,.~.-trt)
> importance(list(bfit1,bfit))
>
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models