Juan and Roger, thanks for the replies.
If I construct the spatially lagged independent variables for each year period, 
add them to the panel dataset, and then use ML estimation from splm package, 
will it work?

Xi

From: Juan Tomas Sayago Gomez [mailto:juantomas.say...@gmail.com]
Sent: Monday, July 15, 2013 6:51 AM
To: roger.biv...@nhh.no
Cc: Chen, Xi Prof.; r-sig-geo@r-project.org
Subject: Re: [R-sig-Geo] Spatial panel Durbin model

Hello,
Yes, to add something to what prof Bivand wrote. to manually create the WX 
remember to use the Kronecker product of the time Identity and the Weight 
matrix. and it should be straight forward.
Best,
Juan.

On Mon, Jul 15, 2013 at 6:45 AM, Roger Bivand 
<roger.biv...@nhh.no<mailto:roger.biv...@nhh.no>> wrote:
On Mon, 15 Jul 2013, Juan Tomas Sayago Gomez wrote:
Hi, package spdep, when you use the command lagsarlm select the option type
mixed.
install.packages("spdep")
library(spdep)
?lagsarlm

Right for cross-section models, but the question was about spatial panel 
models. In that case. it may be necessary to construct the spatial lags 
manually, and add them to the model to be estimated (by ML, for GM you risk 
difficulties with instruments).

Roger

Best,
Juan


On Sun, Jul 14, 2013 at 11:54 PM, Chen, Xi Prof. 
<xi.c...@quinnipiac.edu<mailto:xi.c...@quinnipiac.edu>>wrote:
Hi,
Is there a package that can run spatial panel durbin model in r?

Thanks.
_______________________________________________
R-sig-Geo mailing list
R-sig-Geo@r-project.org<mailto:R-sig-Geo@r-project.org>
https://stat.ethz.ch/mailman/listinfo/r-sig-geo




--
Roger Bivand
Department of Economics, NHH Norwegian School of Economics,
Helleveien 30, N-5045 Bergen, Norway.
voice: +47 55 95 93 55<tel:%2B47%2055%2095%2093%2055>; fax +47 55 95 95 
43<tel:%2B47%2055%2095%2095%2043>
e-mail: roger.biv...@nhh.no<mailto:roger.biv...@nhh.no>



--
Juan Tomás Sayago Gómez
Graduate Research Assistant
West Virginia University - RRI
886 Chestnut Ridge Road, Room 520
P.O. Box 6825
Morgantown, WV 26506-6825

        [[alternative HTML version deleted]]

_______________________________________________
R-sig-Geo mailing list
R-sig-Geo@r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-geo

Reply via email to