Hi Neil
You could tackle this by use of nested factors,
ie. fit 'spring vs rest of year' followed by
'differences between rest of year', and look at
the Wald test for the second term. This will tell you
whether there are differences that you need to take
account of apart from spring, and avoids the
problem of comparing across models, which is tricky.
Hope this helps,
Sue Welham
Biomathematics and Bioinformatics
Rothamsted Research
Harpenden UK AL5 2JQ
E-mail: [log in to unmask]
Tel: +44 (0)1582 763133 ext 2278
Fax: +44 (0)1582 467116
Rothamsted Research is a company limited by guarantee, registered in
England under the registration number 2393175 and a not for profit
charity number 802038.
> -----Original Message-----
> From: GENSTAT-Request [mailto:[log in to unmask]] On
> Behalf Of Neil Walker
> Sent: 20 December 2004 14:58
> To: [log in to unmask]
> Subject: Re: comparing GLMMs
>
>
> hello Genstat list,
>
> I am running an analysis which includes a 4-level explanatory
> variable ("season" , ie spring, summer etc). It is
> significant, but most of the variability appears to be due to
> a positive spring effect. So I have run the model again
> replacing season with a collapsed version "spring vs the rest
> of the world". If this were GLM, the 2 models could be
> compared by means of AIC. I have a feeling this is not so
> straightforward with GLMM due to the more complex
> parameterisation, but I'd be grateful for any suggestions.
> thanks in advance, Neil
> --
> ----------------------------------------------------------------------
> Neil Walker, MSc Phone: +44 (0)1453 861417
> Biostatistician GTN: 5129
> Wildlife Disease Ecology Team Fax: +44 (0)1453 860132
> Central Science Laboratory
> Woodchester Park
> Nympsfield
> Gloucs. GL10 3UJ Web: http://www.csl.gov.uk
> ----------------------------------------------------------------------
>
> Disclaimer
> The information contained in this message may include
> privileged, proprietary or confidential information. Please
> treat it with the same respect that you would expect for your
> own information. If you have received it in error, we
> apologise, and ask that you contact the CSL sender
> immediately and erase it from your computer. Thank you for
> your co-operation.
>
> Further information on confidentiality of our communications,
> can be found at http://www.csl.gov.uk/email.htm
>
|