Abstract:

Because spatial data have the characteristic of spatial autocorrelation, it makes the MLS(Multivariate Linear Regression) model unfit to spatial prediction. Due to account for spatial information, the SAR(Spatial AutoRegression) model can be used for spatial prediction, but it is computationally very expensive. We add spatial information into input variables by replacing each input variables with the weighted average of its neighbors and feed the new input variables to a MLS model to estimate model parameters, and then make spatial prediction, where MLS stands for this model. Experimental results show that the MLS model and the SAR model have almost identical effects on spatial prediction, while the MLS model is computationally more efficient than the SAR model.

Key words: spatial autocorrelation, spatial autoregression model, multivariate linear regression model, spatial prediction.