[R-sig-ME] glmmADMB error: no PSV file found

Moore, Peggy peggy_moore at usgs.gov
Fri Feb 5 22:58:06 CET 2016

I am using glmmadmb (glmmADMB_0.8.3.2 and R2admb_0.7.13) with R version
3.2.1 (2015-06-18) to fit a negative binomial mixed effects model to my
data. Response is repeated measures of plant counts following herbicide
treatments. There are 2 fixed effects (year, treatment) and 2 random
effects (block, plot:block). I successfully fit the model when mcmc=FALSE,
but when I add mcmc=TRUE, I receive the error: no PSV file found.

I noticed that when I load glmmADMB, I receive the warning:
Warning in install.packages :
  package ‘glmmADMB’ is not available (for R version 3.2.1)
Yet I have been running the package and it is in my library. Could there be
a version issue?

I have used save.dir to save output to various locations where I can both
read and write files, including the default location where the binary file
is located. The package writes between 38 and 43 files to the specified
location, including the .dat, .pin. .std files but not the .psv file. It is
not being written anywhere on my drive. I have tried changing many other
settings as well and still receive the error.

I get the same result with the Owls data that comes with the package and an
example from 'Getting Started with glmmADMB.' So, I don't think this is an
issue with the package, per se, but perhaps incompatibilities in my system.

Owls <- transform(Owls, Nest = reorder(Nest, NegPerChick), NCalls =

### No MCMC
OwlModel_nb1_bs <- glmmadmb(NCalls ~ (FoodTreatment + ArrivalTime) *
SexParent +
                                 BroodSize + (1 | Nest), data = Owls,
zeroInflation = TRUE, family = "nbinom1",
                                 save.dir = "C:/Temp")

AIC: 3349.6

                                    Estimate Std. Error z value Pr(>|z|)
(Intercept)                           4.2896     0.8954    4.79  1.7e-06 ***
FoodTreatmentSatiated                -0.9039     0.1404   -6.44  1.2e-10 ***
ArrivalTime                          -0.1194     0.0343   -3.48   0.0005 ***
SexParentMale                         0.4169     1.0527    0.40   0.6921
BroodSize                             0.1982     0.0714    2.78   0.0055 **
FoodTreatmentSatiated:SexParentMale   0.2599     0.1743    1.49   0.1359
ArrivalTime:SexParentMale            -0.0192     0.0433   -0.44   0.6572
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Number of observations: total=599, Nest=27
Random effect variance(s):
            Variance StdDev
(Intercept)   0.1301 0.3607

Negative binomial dispersion parameter: 5.9086 (std. err.: 0.55992)
Zero-inflation: 0.089995  (std. err.:  0.028842 )

Log-likelihood: -1664.8

### With mcmc = TRUE
OwlModel_nb1_bs_mcmc <- glmmadmb(NCalls ~ (FoodTreatment + ArrivalTime) *
SexParent +
                                 BroodSize + (1 | Nest), data = Owls,
zeroInflation = TRUE, family = "nbinom1",
                                 mcmc = TRUE, mcmc.opts =
mcmcControl(mcmc=25000, mcsave=25),
                                 save.dir = "C:/Temp")
debug output:
platform: windows 64
executable name: glmmadmb.exe
saving files into directory C:/Temp
changed working directory to C:/Temp
writing .dat and .pin files
working directory: C:/Temp
Command line: glmmadmb -maxfn 500 -maxph 5 -noinit -shess -mcmc 25000
-mcsave 25 -mcmult 1

Error in R2admb::read_psv(file_name) : no PSV file found
In addition: Warning messages:
1: In glmmadmb(NCalls ~ (FoodTreatment + ArrivalTime) * SexParent +  :
  file glmmadmb.std exists: overwriting
2: running command 'C:\Windows\system32\cmd.exe /c glmmadmb -maxfn 500
-maxph 5 -noinit -shess -mcmc 25000 -mcsave 25 -mcmult 1' had status 42

I have checked online resources and found no resolution and very little
discussion on the subject. I fit the models
with admb.opts=admbControl(run=FALSE) and ran it from the cmd prompt, but I
see the purpose of that exercise is to provide .dat and .pin files to an
ADMB expert to evaluate, and I don't know an expert.

I would really appreciate any tips someone can provide.
Peggy Moore

My sessionInfo in case that's informative:
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

[1] LC_COLLATE=English_United States.1252  LC_CTYPE=English_United
States.1252    LC_MONETARY=English_United States.1252
[4] LC_NUMERIC=C                           LC_TIME=English_United

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base

other attached packages:
[1] R2admb_0.7.13    glmmADMB_0.8.3.2 MASS_7.3-43

loaded via a namespace (and not attached):
 [1] Matrix_1.2-2    plyr_1.8.3      magrittr_1.5    tools_3.2.1
coda_0.17-1     Rcpp_0.11.6     stringi_0.5-5
 [8] nlme_3.1-121    grid_3.2.1      stringr_1.0.0   lattice_0.20-33

	[[alternative HTML version deleted]]

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