Geographically Weighted Regression using a non-euclidean distance metric with simulation data


Lu, Binbin and Charlton, Martin and Fotheringham, Stewart (2012) Geographically Weighted Regression using a non-euclidean distance metric with simulation data. In: Agro-Geoinformatics (Agro-Geoinformatics), 2012 First International Conference on, 2-4 August, 2012, Shangai, China.

[img]
Preview
Download (1MB) | Preview


Share your research

Twitter Facebook LinkedIn GooglePlus Email more...



Add this article to your Mendeley library


Abstract

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 outperforms in the accuracy of coefficient estimates.

Item Type: Conference or Workshop Item (Paper)
Keywords: Geographically Weighted Regression; non-Euclidean distance; Manhattan distance; simulation data; Manhattan distance;
Academic Unit: Faculty of Science and Engineering > Research Institutes > National Centre for Geocomputation, NCG
Item ID: 5754
Depositing User: Martin Charlton
Date Deposited: 02 Feb 2015 16:00
Refereed: Yes
URI:

Repository Staff Only(login required)

View Item Item control page

Document Downloads

More statistics for this item...