[R-sig-ME] Examples of GLMM fits?

[Douglas Bates]

On Sun, Mar 7, 2010 at 2:23 PM,  <Antonio.Gasparrini at lshtm.ac.uk> wrote:
> Dear Douglas Bates and R users,

> some time ago I sent an simulated example with a overdispersed Poisson GLMM where I compare glmmPQL and glmer.
> See https://stat.ethz.ch/pipermail/r-sig-mixed-models/2010q1/003289.html

> I found some problems in the results on glmer with quasipoisson family.
> I hope someone could explain this

I will leave it to others more skilled than I to decide how to
formulate parameter estimates for fictitious distributions.  I have
enough trouble working in the non-fiction end of statistical theory.

> ----------------------------------------------------------------------
>
> Message: 1
> Date: Sat, 6 Mar 2010 09:57:06 -0600
> From: Douglas Bates <bates at stat.wisc.edu>
> To: R-mixed models mailing list <r-sig-mixed-models at r-project.org>
> Subject: [R-sig-ME] Examples of GLMM fits?
> Message-ID:
> <40e66e0b1003060757pa6e772fvfe29960a167e9b76 at mail.gmail.com>
> Content-Type: text/plain; charset=ISO-8859-1
>
> I have added the Gamma family for glmer in the lme4a package and will
> backport to the lme4 package.   (Actually Ben Bolker sent me a patch
> for lme4 several weeks ago and I haven't gotten around to installing
> it yet but will do so.)
>
> However, before I release it I would like to have an example data set
> and model on which to test it.  I don't have any.  Could someone
> provide me with a reference to data and a fitted model that I could
> use as an example?  I would also appreciate an example of a Poisson
> GLMM and other families too.
>
>        [[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>