Determining location influence for shop houses rental value using Geographical Weighted Regression (GWR)
This paper examines the spatial relationship between the rental value of shop house and the influence of location using Geographically Weighted Regression (GWR). GWR attempts to capture spatial variation by calibrating a multiple regresÂsion model fitted at each site of shop house, weighting the lo...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
CRES, FKSG
2006
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/4743/1/DeterminingLocationInfluence.pdf http://eprints.utm.my/id/eprint/4743/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Teknologi Malaysia |
| Language: | English |
| Summary: | This paper examines the spatial relationship between the rental value of shop house and the influence of location using Geographically Weighted Regression (GWR). GWR attempts to capture spatial variation by calibrating a multiple regresÂsion model fitted at each site of shop house, weighting the locational factors from the subject shop house. GWR produces a set of parameter estimates and statistics for the shop houses in the study area. It is evident that the GWR model proÂvides useful information on rental value caused by the surrounding factors. The GWR model is also compared with the traditional ordinary least squares (OLS) model to show the differences of the two models. The parameter estimates and statistics of the GWR and OLS models are then mapped using the Geographic Information system (GIS). Consequently, the influence of site location, bank facilities, shopping complexes and other factors can be evaluated, tested, modelled, and readily visualised. The results show that the location of bank gives rise to a higher significant spatial variation in the rental value of shop house than other factors. It is concluded that, GWR is a useful tool that provides much more information on spatial relationships to assist in model development and in furthering our understanding of spatial processes.
|
|---|