[R-sig-Geo] identical p-value of lm.LMtests (spdep)

[Roger Bivand]

On Thu, 12 Aug 2010, elaine kuo wrote:

> Dear List,
>
> I wanna know if lag or error model is better to examine a spatial regression
> model.
> However, the results of their p-values are the same, which shows no
> difference between the models in the aspect.
> Please kindly help and thanks.

Given the possible errors in your construction of spatial weights in your 
other thread on this list, and the very high levels of residual 
correlation found here, I would not even start trying to consider this 
question. Unless you fully understand what the lag model does, and are an 
econometrician, avoid it. It makes little sense in other fields than 
spatial econometrics, and its interpretation is non-standard. So stay with 
errorsarlm() for error SAR models, or spautolm() for a wider selection of 
error models.

Roger

>
> Elaine
>
>
> code
>
> rm(list=ls())
> datam <-read.csv("c:/migration/Mig_ratio_20100808.csv",header=T,
> row.names=1)
>
> library(ncf)
> library(spdep)
>
>    # get the upper bound
>      up <- knearneigh(cbind(datam$lat,datam$lon))
>      upknn <- knn2nb(up)
>      updist1 <- nbdists(upknn,cbind(datam$lat,datam$lon))
>      updist1
>      updistvec <- unlist(updist1)
>      updistvec
>      upmaxd <- max(updistvec)
>      upmaxd
>
>    # Define coordinates, neighbours, and spatial weights
>      coords<-cbind(datam$lat,datam$lon)
>      coords<-as.matrix(coords)
>
>    # Define neighbourhood (here distance 8)
>      nb8<-dnearneigh(coords,0,8.12)
>      summary(nb8)
>
>      #length(nb8)
>      #sum(card(nb8))
>
>    # Spatial weights, illustrated with coding style "W" (row standardized)
>      nb8.w<-nb2listw(nb8, glist=NULL, style="W")
>
>    # std model
>       datam.sd<-scale(datam)
>       datam.std<-as.data.frame(datam.sd)
>       summary (datam.std)
>       mean(datam.std)
>
>          # obtain standard deviation
>          sd(datam.std)
>
>       mig.std <-lm( datam.std$S ~ datam.std$coast + datam.std$topo_var
> +datam.std$prec_ran, data = datam.std)
>       summary(mig.std)
>
>       mig.lagrange
> <-lm.LMtests(mig.std,nb8.w,test=c("LMerr","RLMerr","LMlag","RLMlag","SARMA"))
>
>       print(mig.lagrange)
>
>
>
>        Lagrange multiplier diagnostics for spatial dependence
>
>
>
> data:
>
> model: lm(formula = datam.std$S ~ datam.std$coast + datam.std$topo_var
> +datam.std$prec_ran, data = datam.std)
>
> weights: nb8.w
>
>
>
> LMerr = 79589.91, df = 1, p-value < 2.2e-16
>
>
>
>
>
>        Lagrange multiplier diagnostics for spatial dependence
>
>
>
> data:
>
> model: lm(formula = datam.std$S ~ datam.std$coast + datam.std$topo_var
> +datam.std$prec_ran, data = datam.std)
>
> weights: nb8.w
>
>
>
> RLMerr = 68943.02, df = 1, p-value < 2.2e-16
>
>
>
>
>
>        Lagrange multiplier diagnostics for spatial dependence
>
>
>
> data:
>
> model: lm(formula = datam.std$S ~ datam.std$coast + datam.std$topo_var
> +datam.std$prec_ran, data = datam.std)
>
> weights: nb8.w
>
>
>
> LMlag = 13000.91, df = 1, p-value < 2.2e-16
>
>
>
>
>
>        Lagrange multiplier diagnostics for spatial dependence
>
>
>
> data:
>
> model: lm(formula = datam.std$S ~ datam.std$coast + datam.std$topo_var
> +datam.std$prec_ran, data = datam.std)
>
> weights: nb8.w
>
>
>
> RLMlag = 2354.020, df = 1, p-value < 2.2e-16
>
>
>
>
>
>        Lagrange multiplier diagnostics for spatial dependence
>
>
>
> data:
>
> model: lm(formula = datam.std$S ~ datam.std$coast + datam.std$topo_var
> +datam.std$prec_ran, data = datam.std)
>
> weights: nb8.w
>
>
>
> SARMA = 81943.93, df = 2, p-value < 2.2e-16
>
> 	[[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-Geo mailing list
> R-sig-Geo at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/r-sig-geo
>

-- 
Roger Bivand
Economic Geography Section, Department of Economics, Norwegian School of
Economics and Business Administration, Helleveien 30, N-5045 Bergen,
Norway. voice: +47 55 95 93 55; fax +47 55 95 95 43
e-mail: Roger.Bivand at nhh.no