[R-sig-ME] [FORGED] Re: Error from glmmTMB().

[Rolf Turner]

On 19/03/20 3:24 pm, Ben Bolker wrote:

> 
>    I did a little more poking around with this.
> 
>    It works (i.e. fits with no warnings with binomial() instead of
> betabinomial().

Yep.

>    It works, sort of (i.e. gives 1 warning about NaN evaluation and a
> non-pos-def Hessian warning, probably from an effectively singular
> model, but gives sensible fixed-effect estimates and std devs) with
> link=logit instead of cloglog.

Yep.

>     Debugging my way through glmmTMB:::fitTMB(), even the first
> evaluation of the objective function gives NaN, and the gradient is a
> vector of NaN values.  I suspect we have a failure to clamp the cloglog
> function somewhere, and may know how to fix it.

I'm impressed.  Wish I had your brains and insight.  Said he, wistfully.

>    This is a very nice, simple example that may help us improve a bunch
> of stuff (it will also help us put some tests in useful places to get
> *slightly* less opaque error messages).
> 
>    I know this doesn't solve your problem immediately - but if I'm lucky
> and have a bit of time I may be able to implement something soon.
> 
>    thanks Rolf!

You are indeed welcome.  I'm glad that you found this example useful. 
Seems to be my main way of contributing to the advancement of 
statistical computing.  I've made similar contributions to Adrian 
Baddeley's spatstat package.  I have come to refer to my propensity for 
stumbling on examples that make software turn to custard as my "Sadim 
Touch".

cheers,

Rolf

-- 
Honorary Research Fellow
Department of Statistics
University of Auckland
Phone: +64-9-373-7599 ext. 88276