Geographically weighted regression and multicollinearity: dispelling the myth

Geographically weighted regression (GWR) extends the familiar regression framework by estimating a set of parameters for any number of locations within a study area, rather than producing a single parameter estimate for each relationship specified in the model. Recent literature has suggested that G...

Full description

Saved in:
Bibliographic Details
Published in:Journal of geographical systems Vol. 18; no. 4; pp. 303 - 329
Main Authors: Fotheringham, A. Stewart, Oshan, Taylor M.
Format: Journal Article
Language:English
Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.10.2016
Springer
Springer Nature B.V
Subjects:
Analysis
Bandwidths
Computer Appl. in Social and Behavioral Sciences
Computer simulation
Econometrics
Economics
Economics and Finance
Estimates
Estimating
Geographic information systems
Geographical Information Systems/Cartography
Geography
Geospatial data
Indicators
Landscape/Regional and Urban Planning
Lung cancer
Mathematical models
Original Article
Parameter estimation
Parameters
Regional/Spatial Science
Regression
Studies
Urban Economics
Variables
C52 Model evaluation, validation, and selection
Collinearity
GWR
Regression diagnostics
C18 Methodological issues: general
Geographically weighted regression
ISSN:1435-5930, 1435-5949
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Geographically weighted regression (GWR) extends the familiar regression framework by estimating a set of parameters for any number of locations within a study area, rather than producing a single parameter estimate for each relationship specified in the model. Recent literature has suggested that GWR is highly susceptible to the effects of multicollinearity between explanatory variables and has proposed a series of local measures of multicollinearity as an indicator of potential problems. In this paper, we employ a controlled simulation to demonstrate that GWR is in fact very robust to the effects of multicollinearity. Consequently, the contention that GWR is highly susceptible to multicollinearity issues needs rethinking.
Bibliography:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:1435-5930
1435-5949
DOI:10.1007/s10109-016-0239-5