mgwrsar (version 0.1-1)

mgwrsar-package: mgwrsar

Description

mgwrsar package proposes functions for estimating linear and local linear model with spatial autocorrelation. It allows to estimate linear and Spatial Autoregressive models with spatially varying coefficients. Models that mixed spatially varying and stationary coefficients can also be estimated. mgwrsar mgwrsar

Details

The DESCRIPTION file: mgwrsar

References

Geniaux, G. and Martinetti, D.(2017). A new method for dealing simultaneously with spatial autocorrelation and spatial heterogeneity in regression models. Regional Science and Urban Economics. (https://doi.org/10.1016/j.regsciurbeco.2017.04.001)

See Also

locfit

Examples

# NOT RUN {
library(mgwrsar)
## loading data example
data(mydata)
coord=as.matrix(mydata[,c("x_lat","y_lon")])
## Creating a spatial weigth matrix (sparce dgCMatrix) of 8 nearest neighbors
W=KNN(coord,8)

ptm1<-proc.time()
model_GWR<-MGWRSAR(formula = 'Y_gwr~X1+X2+X3', data = mydata,coord=coord,
fixed_vars=NULL,kernels=c('gauss'),H=0.13, Model = 'GWR',
control=list(SE=TRUE,doMC=FALSE))
(proc.time()-ptm1)[3]

summary_mgwrsar(model_GWR)
plot_mgwrsar(model_GWR,type='B_coef',var='X2')
plot_mgwrsar(model_GWR,type='t_coef',var='X2')
# }