On Mon, 21 Sep 2009, Bjarke Christensen wrote:


I am looking for a function to make out of sample predictions using
spautolm. The question has been asked before, two years ago, but with no
response: http://finzi.psych.upenn.edu/R/Rhelp02/archive/113162.html.
Certainly, someone must have needed one since?

Clearly not. Predict using just the regression coefficients (with non-spatial weights if used for fitting). If you want simulations around those point estimates, you can introduce spatial autocorrelation with the lambda term, but lambda will not impact the predictions unless the model was misspecified, I believe.


Alternatively, does anyone have a reference or any hints wrt making such a
function? Is there perhaps some reason not to do it?


It could be done, but isn't a high priority - unless you are using non-spatial weights, the speculative predict() method for sarlm objects from errorsarlm() will manage OK.

Hope this helps,

Roger

Thanks in advance,
Bjarke Christensen

_______________________________________________
R-sig-Geo mailing list
[email protected]
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: [email protected]

_______________________________________________
R-sig-Geo mailing list
[email protected]
https://stat.ethz.ch/mailman/listinfo/r-sig-geo

Reply via email to