Skip to content
Prev 2606 / 20628 Next

over-dispersed Poisson with lmer -- a trick, with a catch?

David Atkins wrote:
[snip]
I think so.  It's done in other places (for example, it's exactly
equivalent to what MCMCglmm does), and in Elston et al 2001 (they use a
PQL estimation procedure in Genstat).  (Although "everybody does it"
doesn't *mean* it's correct ...)
Good luck with that ...

  If you can conveniently build from source, you can just comment out
line 1068 (search for "> n =") in lmer.c ...

  cheers
    Ben


Elston, D.A., Moss, R., Boulinier, T., Arrowsmith, C. & Lambin, X.
(2001) Analysis of aggregation, a worked example: numbers of ticks on
red grouse chicks. Parasitology, 122, 563-569.