Conference Publication Details
Mandatory Fields
Lu, BB;Charlton, M;Harris, P
2012 FIRST INTERNATIONAL CONFERENCE ON AGRO-GEOINFORMATICS (AGRO-GEOINFORMATICS)
Geographically Weighted Regression Using a Non-Euclidean Distance Metric with Simulation Data
2012
January
Published
1
0 ()
Optional Fields
267
270
In this study, we investigate the performance of a non-Euclidean distance metric in calibrating a Geographically Weighted Regression (GWR) model with a simulated data set. Random predictor variable and spatially varying coefficients are generated on a square grid of size 20*20. We respectively apply Manhattan and Euclidean distance metrics for the GWR calibrations. The preliminary findings show that Manhattan distance performs significantly better than the traditional choice for GWR - Euclidean distance. In particular, it out-performs in the accuracy of coefficient estimates.
Grant Details