[R-sig-ME] convergence in GLMM (lme4 package)

[Ben Bolker]

Martí Casals <mcasals at ...> writes:

> 
> Hello Ben,
> 
> Thank you so much again. We tried the function but we didn’t achieve to run
> it within our data. However, we found this post (see:
> https://stat.ethz.ch/pipermail/r-sig-mixed-models/2009q2/002413.html),
> which uses a similar function in the example (without an extra space at the
> end of "try-error"):

ok <- function(x,type= "try-error") class(x)!=type*
options(warn=2)*
fitmodel <- try(lmer(modelformula,data))*
ok(fitmodel)*
> 
> and it works in our data.
> 
> Now, we are basically interested in the probability of (non) convergence,
> that's why so far we only want to see how often convergence occurs. In the
> future, we may also want to study the different kinds of warning
> messages....
> 
> Best regards,
> 
> Martí Casals.

  I'm glad you got something to work.  I would be willing to work
on the full problem more, but I can't do much without a reproducible
example ...

   Ben Bolker

 
> 2012/11/1 Ben Bolker <bbolker at ...>
> 
> > On 12-10-31 02:27 PM, Martí Casals wrote:
> > > Hi Ben,
> > > Thank you very much for all your help, so far. Nonetheless, there is
> > > still something not working. If you could have a look at the following
> > > code, I would highly appreciate it. It's about how to count convergence
> > > problems of function glmer within a simulation. I tried to adapt your
> > > proposal to my models, but something's not working, probably to me lack
> > > of knowledge of functions like tryCatch and withCallingHandlers.
> >

  [snip]