[R-sig-ME] Marginal Multinomial Model in R?

Murray Jorgensen maj at waikato.ac.nz
Sat Feb 12 22:30:43 CET 2011

Hi all,
I am consulting in an ecological study in which a number (~80) of 
artificial refuges were placed in a forest patch and site visits (~45) 
were made at which data was collected on the number of adult males and 
females of the insect species of interest in residence at each refuge at 
the time of the visit. (Among other things.)

One figure that I plotted shows the number of refuges in each 'household 
type' ( empty, single male, single female, etc) (5-6 types in all) 
against this visit date. The refuge usage seems strongly seasonal in 
character and influenced by the mating/breeding behaviour of the species.

I had thought that the plot pretty much spoke for itself, but a referee 
wants to see a formal analysis.

It seems that we are in a repeated-measures situation with a multinomial 
response, the sort of situation discussed in Chapter 11 of Agresti's 
Categorical Data Analysis (2nd ed. 2002).

I am looking for help in finding appropriate R packages to analyse this 
data. I found package drm, but that envisages ordinal responses and the 
household types are not ordered in any natural way.

Suggestions would be welcome!

Regards,  Murray
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  majorgensen at ihug.co.nz        Fax 7 838 4155
Phone  +64 7 838 4773 wk    Home +64 7 825 0441   Mobile 021 0200 8350

More information about the R-sig-mixed-models mailing list