[ADMB Users] glmmADMB error message

[Mollie Brooks]

Hi Lisa,
It looks like you have the syntax wrong. You may want to try
> model2<-glmm.admb(aabundm2~babundm2+tramplingf*litterf,random=~1,group="block", data=exp, family='nbinom')
This wil give each block a random intercept. 

There's a new version coming out soon which has a syntax more familiar to R users.They just need to get the binaries built. See http://glmmadmb.r-forge.r-project.org/ for updates.
best,
Mollie

Mollie Brooks
Ph.D. Candidate
NSF IGERT Fellow
Biology Department
University of Florida
mbrooks at ufl.edu
www.zoology.ufl.edu/mbrooks



On 2 Aug 2011, at 3:18 AM, Lisa Denmead wrote:

> Hi,
>  
> Up until earlier today I have been using glmmADMB with no real issues, but now every model I try and run comes up with the error below, even though I have run it with this data before. I have been in contact with some other students using this and they seem to be having the same problem, yet none of us can figure out where we are going wrong. Any advice would be greatly appreciated!
>  
> > model2<-glmm.admb(aabundm2~babundm2+tramplingf*litterf,random=~1|block,group="group", data=exp, family='nbinom')
>  1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
>  
>  - final statistics:
> 13 variables; iteration 0; function evaluation 0
> Function value -1.#INDe+000; maximum gradient component mag -1.#INDe+000
> Exit code = 0;  converg criter  1.0000e-004
> Var   Value    Gradient   |Var   Value    Gradient   |Var   Value    Gradient  
>   1  0.0000 -1.#INDe+000 |  2  0.0000 -1.#INDe+000 |  3  0.0000 -1.#INDe+000
>   4  0.0000 -1.#INDe+000 |  5  0.0000 -1.#INDe+000 |  6  0.0000 -1.#INDe+000
>   7  0.0000 -1.#INDe+000 |  8  0.0000 -1.#INDe+000 |  9  0.0000 -1.#INDe+000
>  10  0.0000 -1.#INDe+000 | 11  0.0000 -1.#INDe+000 | 12  0.0000 -1.#INDe+000
>  13  0.0000 -1.#INDe+000 |
>  
>  - final statistics:
> 13 variables; iteration 0; function evaluation 0
> Function value -1.#INDe+000; maximum gradient component mag -1.#INDe+000
> Exit code = 0;  converg criter  1.0000e-004
> Var   Value    Gradient   |Var   Value    Gradient   |Var   Value    Gradient  
>   1  0.0000 -1.#INDe+000 |  2  0.0000 -1.#INDe+000 |  3  0.0000 -1.#INDe+000
>   4  0.0000 -1.#INDe+000 |  5  0.0000 -1.#INDe+000 |  6  0.0000 -1.#INDe+000
>   7  0.0000 -1.#INDe+000 |  8  0.0000 -1.#INDe+000 |  9  0.0000 -1.#INDe+000
>  10  0.0000 -1.#INDe+000 | 11  0.0000 -1.#INDe+000 | 12  0.0000 -1.#INDe+000
>  13  0.0000 -1.#INDe+000 |
>  inner maxg = -1.#IO  Inner f = -1.#IO
>  f = -1.#IND max g = 1.#QNAN
> Newton raphson 1  Error in matrix inverse -- matrix singular in inv(dmatrix)
> Error in matrix inverse -- matrix singular in inv(dmatrix)
> Error in glmm.admb(aabundm2 ~ babundm2 + tramplingf * litterf, random = ~1 |  :
>   The function maximizer failed
> In addition: Warning messages:
> 1: running command 'C:\Windows\system32\cmd.exe /c "C:/Users/20731259/Documents/R/win-library/2.13/glmmADMB/bin/windows/nbmm.exe" -maxfn 500 ' had status 1
> 2: In shell(cmd, invisible = TRUE) :
>   '"C:/Users/20731259/Documents/R/win-library/2.13/glmmADMB/bin/windows/nbmm.exe" -maxfn 500 ' execution failed with error code 1
>  
> Thanks,Lisa
> _______________________________________________
> Users mailing list
> Users at admb-project.org
> http://lists.admb-project.org/mailman/listinfo/users

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.admb-project.org/pipermail/users/attachments/20110802/a57595d1/attachment.html>