Please read ?lagsarlm under the tol.solve= item: the tolerance for detecting linear dependencies in the columns of matrices to be inverted - passed to \code{solve()} (default=1.0e-10). This may be used if necessary to extract coefficient standard errors (for instance lowering to 1e-12), but errors in \code{solve()} may constitute indications of poorly scaled variables: if the variables have scales differing much from the autoregressive coefficient, the values in this matrix may be very different in scale, and inverting such a matrix is analytically possible by definition, but numerically unstable; rescaling the RHS variables alleviates this better than setting tol.solve to a very small value
Does that help? -- Roger Bivand NHH Norwegian School of Economics Helleveien 30, 5045 Bergen, Norway roger.biv...@nhh.no ________________________________________ Fra: r-sig-geo-boun...@r-project.org [r-sig-geo-boun...@r-project.org] på vegne av Milan Sharma [milansharma2...@yahoo.com] Sendt: 29. desember 2012 7:43 To: r-sig-geo@r-project.org Emne: [R-sig-Geo] fitting lag model in R Hi all, can any one of you see whats wrong in the code below? > model<-lm(Tcrash~X100MVMT+Alcohol+Alignment+PVMT, data=data)#works > sar<-spautolm(Tcrash~X100MVMT+Alcohol+Alignment+PVMT,listw=WI_queenW, > data=data)#works > lag <- lagsarlm(Tcrash~X100MVMT+Alcohol+Alignment+PVMT, data=data, > listw=listwW)#shows error Error in solve.default(inf, tol = tol.solve) : system is computationally singular: reciprocal condition number = 2.44638e-12 > lag <- lagsarlm(Tcrash~X100MVMT+Alcohol+Alignment+PVMT, data=data, > listw=WI_queenW) Error in solve.default(inf, tol = tol.solve) : system is computationally singular: reciprocal condition number = 1.51647e-13 > WI_queenW Characteristics of weights list object: Neighbour list object: Number of regions: 71 Number of nonzero links: 364 Percentage nonzero weights: 7.22079 Average number of links: 5.126761 Weights style: B Weights constants summary: n nn S0 S1 S2 B 71 5041 364 728 8160 ............................. Milan [[alternative HTML version deleted]] _______________________________________________ R-sig-Geo mailing list R-sig-Geo@r-project.org https://stat.ethz.ch/mailman/listinfo/r-sig-geo