www.cmm.bristol.ac.uk/forum

Hi,

I am new to multilevel modeling and this forum and hoping that someone may be able to help me with a quick question. I am fitting a spatial model for a binomial response variable(proportions). But I couldn't find any example in the MLwiN user guide or in the guide for MCMC estimation in MLwiN. Would anyone point me to a reference/example that performs such an analysis? Thanks.

Dear user,
I'll be honest with you and say that I am not sure I have ever tried a binary response model with spatial random effects. The majority of the time in disease mapping which is the field for which I coded the CAR modelling section the responses are treated as counts and fitted as Poisson. It might be worth checking the literature to see if people have in fact fitted such models (probably in WinBUGS). I would also caution therefore to use the MLwiN->WinBUGS interface to check you get similar answers from the 2 packages due to lack of examples of use.
Hope this helps,
Bill.