[R-sig-Geo] neg bin models with errorsalm and lagsarlm

[Roger Bivand]

On Tue, 28 Nov 2006, Jeffrey Stratford wrote:

> Hi folks,
> 
> Is it appropriate to use a negative binomial with errorsalm and
> lagsarlm?  If not is there an alternative to do spatial error and
> spatial models with a negative binomial?  

The spatial regression fitting functions are written for an assumed 
continuous dependent variable with Gaussian errors, so they are not 
suitable for the negative binomial case. You could try the autocov_dist 
function or equivalents on its help page as a quick fix, otherwise this 
probably looks like WinBUGS with your choice of CAR.

Roger

> 
> Thanks,
> 
> Jeff
> 
> ****************************************
> Jeffrey A. Stratford, Ph.D.
> Postdoctoral Associate
> 331 Funchess Hall
> Department of Biological Sciences
> Auburn University
> Auburn, AL 36849
> 334-329-9198
> FAX 334-844-9234
> http://www.auburn.edu/~stratja
> 
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
> 

-- 
Roger Bivand
Economic Geography Section, Department of Economics, Norwegian School of
Economics and Business Administration, Helleveien 30, N-5045 Bergen,
Norway. voice: +47 55 95 93 55; fax +47 55 95 95 43
e-mail: Roger.Bivand at nhh.no