CODEWITHSUNDEEP
r
swihart
swihart

Reputation: 2738

glmmadmb R package: Error in process_randformula(formula, random, data = data) and Error in `colnames<-`(`*tmp*`, value = character(0))

I want to fit zero inflated negative binomial random effect models using glmmadmb() in R. These are reproducible as they use data from the package.

Attempt 1:

om1 <- glmmadmb(SiblingNegotiation~FoodTreatment*SexParent+offset(log(BroodSize)),
                random=(1|Nest),
                zeroInflation=TRUE,family="nbinom",data=Owls)

gives the error:

Error in process_randformula(formula, random, data = data) : 
  object 'Nest' not found

Attempt 2:

om2 <- glmmadmb(SiblingNegotiation~FoodTreatment*SexParent+offset(log(BroodSize)),
                random="~1|Nest",
                zeroInflation=TRUE,family="nbinom",data=Owls)

gives the error:

Error in `colnames<-`(`*tmp*`, value = character(0)) : 
  attempt to set 'colnames' on an object with less than two dimensions

How can I successfully do this function call with the random argument?

Upvotes: 1

Views: 105

Answers (1)

swihart
swihart

Reputation: 2738

So to fit this model with the random argument, try removing the quotes from your Attempt 2 code:

om3 <- glmmadmb(SiblingNegotiation~FoodTreatment*SexParent+offset(log(BroodSize)),
                random=~1|Nest,
                zeroInflation=TRUE,family="nbinom",data=Owls)

or use as.formula and the quotes:

om4 <- glmmadmb(SiblingNegotiation~FoodTreatment*SexParent+offset(log(BroodSize)),
                random=as.formula("~1|Nest"),
                zeroInflation=TRUE,family="nbinom",data=Owls)

Which is equivalent to the example given on the help page for glmmadmb(), which does not use the random argument:

om5 <- glmmadmb(SiblingNegotiation~FoodTreatment*SexParent+
                 (1|Nest)+offset(log(BroodSize)),
               zeroInflation=TRUE,family="nbinom",data=Owls)

> identical(om3$fitted, om5$fitted)
[1] TRUE
> identical(om4$fitted, om5$fitted)
[1] TRUE
> identical(om3$fitted, om4$fitted)
[1] TRUE

Upvotes: 2

Related Questions