[R-sig-ME] STD file not found error with glmmADMB

[Joshua Wiley]

Hi Melanie,

This bit, "function maximizer failed" suggests that it is having
difficulty estimating your model.  What happens if you try a simpler
model, (the simplest being intercept only)?  My memory is vague, but
it seems like Ben Bolker may have said at one point that using
variables from the global environment was not tested much in
glmmadmb(), so you might also try using the data argument.  Which
segues nicely into my last point, which is that it would be helpful to
at least show us the output from

str(yourdataset)

so that we know the size, types of variables, etc.

Cheers,

Josh

On Sun, Jun 24, 2012 at 4:57 AM, Melanie Browne
<meluchbrowne at hotmail.com> wrote:
>
> Hello, I am using the glmmADMB package (I downloaded it using: install.packages("glmmADMB", repos="http://r-forge.r-project.org"), I am not sure which version it is). I'm on R version 2.15.1 GUI 1.52 Leopard build 64-bit, and yes, I'm on a mac.
> I'm trying to run the following function: fit= glmmadmb(fruit ~ surroundings*town+(1|site), family='nbinom1', zeroInflation=TRUE)
> and got the following error: dyld: unknown required load command 0x80000022Error in glmmadmb(fruit ~ surroundings * town + (1 | site), family = "nbinom1",  :   The function maximizer failed (couldn't find STD file)
> My variables are fruit counts and there is overdispersion.
> I added the zeroInflation because I read that it worked that way but in my case it still didn't. I also tried to download an older version of the package that I saw you recommended to someone. (I also tried with admb.opts=admbControl(shess=FALSE,noinit=FALSE)). Now I get the following error:Error in parse(text = lab) : object 'lab' not foundIn addition: Warning message:In is.na(rows) : is.na() applied to non-(list or vector) of type 'NULL'
> I hope I have provided enough information and that my problem is clear enough...
> Do you have any ideas that could help me resolve this problem? Or do you know of another package that would let me do a negative binomial with mixed factors? (I don't think the zero-inflated part is a problem).
> Thank you very much,
> Melanie Browne
>        [[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models



-- 
Joshua Wiley
Ph.D. Student, Health Psychology
Programmer Analyst II, Statistical Consulting Group
University of California, Los Angeles
https://joshuawiley.com/