[R] spatial estimation

[Roger Bivand]

fabrizio renzi <fabrizio.renzi84 <at> gmail.com> writes:

> 
> I am using spdep package to do spatial estimations in R.
> 
> Anyway I was not able to find out how to compute the loglikelihood (and a
> pseudo-R^2) of a 2sls spatial model, estimated through the command stsls. I
> need some fitting indicator to compare the 2sls model with the one obtained
> through maxL (command lagsarlm).
> 

When the poster wrote to me off-list a week ago, I replied:

"Please *do* write to the R-sig-geo list rather than to me directly -
others can answer your question as well, perhaps better, and in a more
timely way than I can. In addition, threads in the list can be searched in
the archives, so others can avoid the same problem later.

Please when you post indicate the published paper defining the LL of this
GMM-estimated model."

It is instructive to run:

library(sem)
logLik(tsls(Q ~ P + D, ~ D + F + A, data=Kmenta))

which explains why I asked for a publication providing something which
doesn't spring naturally from the estimation method.

Roger Bivand



> Thanks for your answer,
> 
> Regards
>