[ADMB Users] glmmADMB-Function maximizer failed Poisson, ZIPoisson, NB1, ZINB1

Ben Bolker bbolker at gmail.com
Thu Dec 15 08:53:32 PST 2011


  If you get the very latest version of glmmADMB (i.e. re-install from
r-forge)  you should be able to do the following:


step 1

glmmadmb(...,admb.opts=admbControl(run=FALSE),debug=TRUE,save.dir="glmmtmp")

  This should set up a temporary 'glmmtmp' directory (or whatever you
want to call it), copy the glmmadmb binary over to that directory (if
necessary -- this only happens on MacOS and Linux, not on Windows), and
create the glmmadmb.dat and glmmadmb.pin input files.  It should also
generate output that tells you what command would be run by glmmADMB to
run the model.

step 2

  change to the temporary directory and run the command (which in your
case would be

C:\WINDOWS\system32\cmd.exe /c "C:/Program
Files/R/R-2.14.0/library/glmmADMB/bin/windows32/glmmadmb.exe" -maxfn 500
-noinit

 step 3 (optional) if you successfully run the glmmadmb binary outside
of R and then want to import the information back into R, you can run
the code from step 1 again within R; this time it will find the output
files that have been created.

  Let me know how it goes.

  Ben Bolker


On 11-12-15 03:55 PM, Rocio Jana wrote:
> Hello again
> 
> Thank you Ben for the advice. I already had tried adding: (second
> formula I posted in previous message)
> 
> admb.opts=admbControl(shess=FALSE,noinit=FALSE)
> 
> Also tried now
> 
> admb.opts=admbControl(shess=FALSE)
> 
> But I still receive the error
> 
> 
>  - final statistics:
> 8 variables; iteration 28; function evaluation 32
> Function value   1.2095e+03; maximum gradient component mag  -3.6290e-05
> Exit code = 1;  converg criter   1.0000e-04
> Var   Value    Gradient   |Var   Value    Gradient   |Var   Value    Gradient
>  1 45.43909  3.33461e-07 |  2 -2.39643 -8.71364e-07 |  3 -0.24019  1.08903e-06
>  4  4.47829 -8.06363e-07 |  5 -0.04157 -1.52222e-06 |  6 -5.52336 -5.95947e-07
>  7 -0.40882  1.30698e-06 |  8  0.47812 -3.62897e-05 |
> Hessian type 4
>  inner maxg = -0.001902  Inner second time = -0.001902  Inner f = 1191
>  f = 1190.630581903201 max g = 0.001901642282498399
> Newton raphson 1  Error in glmmadmb(mataicl ~ rimuover + kahikover +
> mataiover + miroover +  :
>  The function maximizer failed
> In addition: Warning messages:
> 1: running command 'C:\WINDOWS\system32\cmd.exe /c "C:/Program
> Files/R/R-2.14.0/library/glmmADMB/bin/windows32/glmmadmb.exe" -maxfn
> 500 -noinit' had status 1
> 2: In shell(cmd, invisible = TRUE) :
>  '"C:/Program Files/R/R-2.14.0/library/glmmADMB/bin/windows32/glmmadmb.exe"
> -maxfn 500 -noinit' execution failed with error code 1
> 
> 
> The instructions to try the optimizer outside of R will very
> appreciated. Thank you very much.
> 
> Rocio
> 
> 
> Rocio C. Jaña Prado PhD candidate
> School of Biological Sciences
> University of Canterbury Te Whare Wananga o Waitaha
>  Private Bag 4800, Christchurch 8020
>  New Zealand
> Phone: +64 3 3643055 or ext 3055 Fax: +64 3 3642590
> 
> 




More information about the Users mailing list