[R-sig-ME] glmmADMB error: Invalid index for array

Ben Bolker bbolker at gmail.com
Mon Feb 15 05:46:50 CET 2016


Moore, Peggy <peggy_moore at ...> writes:

> 
> I am fitting models to investigate the relationship between herbicide
> treatment and species response using the R package glmmADMB with 2 fixed
> (treatment, year) and 2 random (block, plot) effects. I would like to use
> MCMC to improve estimates and confidence limits. Model fit and output is
> sensible without mcmc, but when mcmc=TRUE, the response is simply 'no PSV
> file found', i.e., no output, and model output is not produced. When I run
> the executable from the cmd prompt, I receive an invalid-index error.
> For example, using the Owls data set that comes with the package, the
> following model from Getting Started with glmmADMB by Bolker et al., and
> this same process, the error is: Invalid index 11 used for array range [1,
> 10] in "double& dvector::operator [] (int i)":
> 
> OwlModel_nb1_bs <- glmmadmb(NCalls ~ (FoodTreatment + ArrivalTime) *
> SexParent +
>                                  BroodSize + (1 | Nest), data = Owls,
> zeroInflation = TRUE,
>                                  family = "nbinom1",
>                                  mcmc = TRUE, mcmc.opts =
> mcmcControl(mcmc=25000, mcsave=25),
>                                  debug=TRUE,
> admb.opts=admbControl(run=TRUE,
>                                  noinit=FALSE, shess=FALSE),
>                                  save.dir = "C:/Temp/glmm")
> I would appreciate any recommendations on how I might avoid this error.
> Peggy


Hmm.  I just ran approximately the same thing on my machine, and couldn't
get it to break.  I didn't run it for as long, but otherwise everything else
was (I think) identical.  Did you look in your temp directory?  is there
a .PSV file there?


OwlModel_nb1_bs <- glmmadmb(SiblingNegotiation ~ 
              (FoodTreatment + ArrivalTime) *
                             SexParent +
                                 BroodSize + (1 | Nest), data = Owls,
                               zeroInflation = TRUE,
                                 family = "nbinom1",
                                 mcmc = TRUE, mcmc.opts =
                            mcmcControl(mcmc=100, mcsave=5),
                                 debug=TRUE,
                         admb.opts=admbControl(run=TRUE,
                                 noinit=FALSE, shess=FALSE),
                                 save.dir="tmpadmb")


> My sessionInfo()
> R version 3.2.1 (2015-06-18)
> Platform: x86_64-w64-mingw32/x64 (64-bit)
> Running under: Windows 7 x64 (build 7601) Service Pack 1
> 
> attached base packages:
> [1] stats     graphics  grDevices utils     datasets  methods   base
> 
> other attached packages:
> [1] pastecs_1.3-18   boot_1.3-17      MCMCglmm_2.21    ape_3.3
>  coda_0.17-1      Matrix_1.2-2     ggplot2_1.0.1
> [8] glmmADMB_0.8.3.3 MASS_7.3-43
> 
> loaded via a namespace (and not attached):
>  [1] Rcpp_0.11.6      magrittr_1.5     munsell_0.4.2    colorspace_1.2-6
> lattice_0.20-33  stringr_1.0.0    plyr_1.8.3
>  [8] tools_3.2.1      grid_3.2.1       gtable_0.1.2     nlme_3.1-121
> corpcor_1.6.8    htmltools_0.2.6  yaml_2.1.13
> [15] digest_0.6.8     tensorA_0.36     R2admb_0.7.5.3   reshape2_1.4.1
> rmarkdown_0.8    stringi_0.5-5    scales_0.2.5
> [22] proto_0.3-10
> 
> 	[[alternative HTML version deleted]]
> 
>



More information about the R-sig-mixed-models mailing list