An embedded and charset-unspecified text was scrubbed... Name: not available URL: <https://stat.ethz.ch/pipermail/r-sig-geo/attachments/20120626/cae3770b/attachment.pl>
interpreting SAR and CAR outputs
3 messages · Mitra Devkota, Juan Tomas Sayago, Corey Sparks
An embedded and charset-unspecified text was scrubbed... Name: not available URL: <https://stat.ethz.ch/pipermail/r-sig-geo/attachments/20120626/109a5139/attachment.pl>
Hi, I would examine the Lagrange multiplier specification tests from a lm() fit. like: fit1<-lm(yield~Temp+precept, data=data) lm.LMtest(fit1, listw=ND_queenW, test="all") and see which of the tests has the "largest" significant test statistic. That will let you know if your data follow a lag or error process. It may be appropriate to fit a model with lagsarlm(). Overall I would say there is not much difference between these two models, based on the small difference in AIC, it really depends on whether you believe the way each is modeling the data, SAR specification, versus the first order Markov assumption of the CAR model. I would definitely check out the specification tests. Best, Corey Corey Sparks Assistant Professor Department of Demography College of Public Policy 501 West Cesar E Chavez Blvd Monterrey Building 2.270C San Antonio, TX 78207 corey.sparks 'at' utsa.edu 210 458 3166 ----- Corey Sparks Assistant professor Department of Demography The University of Texas at San Antonio 501 West Cesar E Chavez Blvd San Antonio TX 78207 Corey.sparks 'at' utsa.edu 210 458 3166 <tel:210%20458%203166> Latitude: 29.423614 / Longitude: -98.504282 -- View this message in context: http://r-sig-geo.2731867.n2.nabble.com/interpreting-SAR-and-CAR-outputs-tp7580342p7580348.html Sent from the R-sig-geo mailing list archive at Nabble.com.