Wrt. question 1 - use a symmetric style, for example B or C, not W (row standardisation). CAR should not be used with asymmetric weights. Wrt. question 2 - no, there are no prediction methods for spautolm output objects, but the predictions would be the product of the aspatial coefficient estimates and the newdata values, as in the case of the predictions for SAR errorsarlm objects for newdata. The spatial coefficient affects the residual, so will impact the variance of the prediction rather than the point estimate (I believe). There is a discussion in Kaluzny et al. 1998 - the S-Plus spatial stats module book. Hope this helps, Roger --- Roger Bivand, NHH, Helleveien 30, N-5045 Bergen, [email protected]
________________________________ Fra: [email protected] på vegne av ONKELINX, Thierry Sendt: lø 11.04.2009 17:47 Til: [email protected] Emne: [R-sig-Geo] Questions about spautolm Dear all, I have a few questions about spautolm from the spdep package. I get warning about "Assymetric weights" with family = "CAR". The weights are defined like the code below. The dataset is roughly based on a 1000 x 500m grid. But only the gridpoints in forest are measured. Hence it is not possible to get symmetric weights. Is this violating an assumuption of the model? Or can this cause another problem? Buren <- dnearneigh(cbind(dataset$X, dataset$Y), d1 = 0, d2 = 6500) Weights <- nb2listw(Buren, style = "W", zero.policy = TRUE) My second question is about prediction. Is it possible to use a spautolm model to make predictions for other locations? Regards, Thierry ------------------------------------------------------------------------ ---- ir. Thierry Onkelinx Instituut voor natuur- en bosonderzoek / Research Institute for Nature and Forest Cel biometrie, methodologie en kwaliteitszorg / Section biometrics, methodology and quality assurance Gaverstraat 4 9500 Geraardsbergen Belgium tel. + 32 54/436 185 [email protected] www.inbo.be To call in the statistician after the experiment is done may be no more than asking him to perform a post-mortem examination: he may be able to say what the experiment died of. ~ Sir Ronald Aylmer Fisher The plural of anecdote is not data. ~ Roger Brinner The combination of some data and an aching desire for an answer does not ensure that a reasonable answer can be extracted from a given body of data. ~ John Tukey Dit bericht en eventuele bijlagen geven enkel de visie van de schrijver weer en binden het INBO onder geen enkel beding, zolang dit bericht niet bevestigd is door een geldig ondertekend document. The views expressed in this message and any annex are purely those of the writer and may not be regarded as stating an official position of INBO, as long as the message is not confirmed by a duly signed document. _______________________________________________ R-sig-Geo mailing list [email protected] https://stat.ethz.ch/mailman/listinfo/r-sig-geo [[alternative HTML version deleted]]
_______________________________________________ R-sig-Geo mailing list [email protected] https://stat.ethz.ch/mailman/listinfo/r-sig-geo
