[R-sig-ME] modelling proportions, with aggregated data, and the new/old lme4

[Ben Bolker]

Joerg Luedicke <joerg.luedicke at ...> writes:

> 
> Hi Ben and Fredrik,
> 
> Thanks for the comments and the proof! Next time I will be less hasty
> in responding...
> 
> Cheers,
> 
> Joerg

   Don't forget that I was wrong too (I forgot about the conditioning). 
 I know that this (i.e. using the Poisson model with an offset to
model binomial data) is a common practice, maybe it was done in the past for
computational reasons?

library("fortunes")
fortune("great-great grandchildren")

  cheers
    Ben