Hi,all I am using the spdep-package to estimate the SAR(or called SLM) and SDM in R. I can get the estimation results of SAR and SDM with the command of "lagsarlm". But when I perform the "impact" command to calculate the direct effect, indirect effect and total effect, it feedback the following sentences:"Error in impacts.sarlm(s.lag, mat2listw(swmmat)) : Only row-standardised weights supported". I used the same matrix, whcih I built in ArcGIS 10.1 based on the principle of "inversed distance" with row standarised, and then it was converted into R. I have tried many times. Can you tell me what else I need to do to calculate the impacts and tell me the codes. Thank you so much!
Best regards. Yours sincerely, Wenyue Yang *The codes I put into R is presented as follow:* >v=read.csv(file=file.choose(),header=T) >library(spdep) >swm<-read.table(file=file.choose(),header=T,sep=",")# I choose the text file of matrix built in ArcGIS >n=length(unique(swm[[3]])) >swmmat<-matrix(0,n,n) >apply(swm,1,function(x)swmmat[x[3],x[4]]<<-x[5]) >setequal(swm$ID, v$ID) >dimnames(swmmat)<-list(v$ID,v$ID) >swmmat<-swmmat[v$ID,v$ID] >fm=SJgap~BSD+MSD+RND >s.lag<-lagsarlm(fm,data=v,listw=mat2listw(swmmat)) >impacts(s.lag, mat2listw(swmmat)) Error in impacts.sarlm(s.lag, mat2listw(swmmat)) : Only row-standardised weights supported OR > W <- as(mat2listw(swmmat), "CsparseMatrix") > trMatc <- trW(W, type="mult") > impacts(s.lag, trMatc) Error in impacts.sarlm(s.lag, trMatc) : Only row-standardised weights supported -- View this message in context: http://r.789695.n4.nabble.com/Why-I-get-the-massage-of-Error-in-impacts-sarlm-s-lag-mat2listw-swmmat-Only-row-standardised-weights-tp4710356.html Sent from the R help mailing list archive at Nabble.com. ______________________________________________ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
