[R-sig-ME] Quasilikelihood considered harmful? was: Examples of GLMM fits?

[Douglas Bates]

On Mon, Mar 8, 2010 at 2:30 PM, Murray Jorgensen <maj at waikato.ac.nz> wrote:
> Doug's response indicates a certain scepticism about quasilikelihood and
> it's use in modelling. I am quite interested in this question and may even
> get around to attempting some theoretical work about it. What I would like
> to know about literature and discussions critical of QL and its role in
> modelling. I think I am generally aware of pro-QL literature.

I should have been more specific and less cheeky.  What I am trying to
communicate is that the way that I have been able to finally work out
in my mind how to estimate parameters in generalized linear mixed
models is to go right back to the probability model and derive things
from there, step by step.  I can't do that for quasi-poisson or
quasi-binomial models because there is no probability model.

I don't know what is involved in fitting parameters using
quasilikelihood and whether or not the approach can be generalized to
mixed models.  I find it hard enough to work out what all the bits and
pieces are when working with a probability distribution.  Working with
something that sort of looks like a probability distribution but isn't
really is beyond what I want to try at this point.


> Cheers,  Murray Jorgensen
>
> On 9/03/2010 3:50 a.m., Douglas Bates wrote:
> [...]
>>
>> 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.
>>
> [...]
> --
> Dr Murray Jorgensen      http://www.stats.waikato.ac.nz/Staff/maj.html
> Department of Statistics, University of Waikato, Hamilton, New Zealand
> Email: maj at waikato.ac.nz                                Fax 7 838 4155
> Phone  +64 7 838 4773 wk    Home +64 7 825 0441   Mobile 021 0200 8350
>