[R-sig-ME] MCMCglmm with zibinomial

[Jarrod Hadfield]

Hi,

Binary binomial (categorical) data cannot be zero-inflated, only  
binomial data with >1 trials. MCMCglmm is expecting a binomial  
response in the form cbind(successes, failures).

Cheers,

Jarrod




Quoting "ONKELINX, Thierry" <Thierry.ONKELINX at inbo.be> on Tue, 21 Jun  
2011 13:58:51 +0000:

> Dear all,
>
> I am trying to fit a zibinomial model with MCMCglmm. Everything  
> works fine when I do the non-inflated model. But the zi models  
> throws an error. Any suggestions on what when wrong?
>
> Best regards,
>
> Thierry
>
> library(MCMCglmm)
>
> nYear <- 20
> nSite <- 50
> nVisit <- 5
> Start <- qlogis(0.7)
> TrendOC <- -0.1
> Detect <- 0.6
> sdSite <- 1
> Design <- expand.grid(Year= seq_len(nYear), Site = seq_len(nSite),  
> Visit = seq_len(nVisit))
> RFSiteOC <- rnorm(nSite, sd = sdSite)
> Design$Occupancy <- plogis(with(Design, Start + (Year - 1) * TrendOC  
> + RFSiteOC[Site]))
> Design$Detect <- Detect
> Design$Site <- factor(Design$Site)
>
> set.seed(123456)
> Design$Present <- rbinom(nrow(Design), size = 1, prob =  
> Design$Occupancy) * rbinom(nrow(Design), size = 1, prob =  
> Design$Detect) == 1
>
> #this works fine
> prior <- list(R = list(V = 1, fix = 1), G = list(G1 = list(V = 1, nu  
> = 0.002)))
> m <- MCMCglmm(Present ~ Year, random = ~Site, rcov = ~units, data =  
> Design, family = "categorical", prior = prior)
> plot(m)
>
> #this throws an error
> priorzi <- list(R = list(V = diag(2), fix = 2), G = list(G1 = list(V  
> = 1, nu = 0.002)))
> mzi <- MCMCglmm(Present ~ Year, random = ~Site, rcov =  
> ~idh(trait):units, data = Design, family = "zibinomial", prior =  
> priorzi)
> #the error
> Error in rowSums(data[, match(response.names[0:1 + nt], names(data))]) :
>   error in evaluating the argument 'x' in selecting a method for  
> function 'rowSums': Error in `[.data.frame`(data, ,  
> match(response.names[0:1 + nt], names(data))) :
>   undefined columns selected
>
>
>
>
>> sessionInfo()
> R version 2.13.0 (2011-04-13)
> Platform: i386-pc-mingw32/i386 (32-bit)
>
> locale:
> [1] LC_COLLATE=Dutch_Belgium.1252  LC_CTYPE=Dutch_Belgium.1252
> [3] LC_MONETARY=Dutch_Belgium.1252 LC_NUMERIC=C
> [5] LC_TIME=Dutch_Belgium.1252
>
> attached base packages:
> [1] stats     graphics  grDevices utils     datasets  methods   base
>
> other attached packages:
> [1] MCMCglmm_2.12      corpcor_1.5.7      ape_2.7-2          coda_0.14-4
> [5] Matrix_0.9996875-0 lattice_0.19-28    tensorA_0.36       rj_0.5.5-4
>
> loaded via a namespace (and not attached):
> [1] gee_4.13-16  grid_2.13.0  nlme_3.1-101 tools_2.13.0
> ----------------------------------------------------------------------------
> ir. Thierry Onkelinx
> Instituut voor natuur- en bosonderzoek
> team Biometrie & Kwaliteitszorg
> Gaverstraat 4
> 9500 Geraardsbergen
> Belgium
>
> Research Institute for Nature and Forest
> team Biometrics & Quality Assurance
> Gaverstraat 4
> 9500 Geraardsbergen
> Belgium
>
> tel. + 32 54/436 185
> Thierry.Onkelinx at inbo.be
> www.inbo.be
>
> To call in the statistician after the experiment is done may be no  
> more than asking him to perform a post-mortem examination: he may be  
> able to say what the experiment died of.
> ~ Sir Ronald Aylmer Fisher
>
> The plural of anecdote is not data.
> ~ Roger Brinner
>
> The combination of some data and an aching desire for an answer does  
> not ensure that a reasonable answer can be extracted from a given  
> body of data.
> ~ John Tukey
>
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>
>



-- 
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.