Geographically weighted regression and multicollinearity: dispelling the myth

Stewart Fotheringham, Taylor M. Oshan

Research output: Contribution to journalArticlepeer-review

187 Scopus citations

Abstract

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.

Original languageEnglish (US)
Pages (from-to)303-329
Number of pages27
JournalJournal of Geographical Systems
Volume18
Issue number4
DOIs
StatePublished - Oct 1 2016

Keywords

  • Collinearity
  • GWR
  • Geographically weighted regression
  • Regression diagnostics

ASJC Scopus subject areas

  • Geography, Planning and Development
  • Earth-Surface Processes

Fingerprint

Dive into the research topics of 'Geographically weighted regression and multicollinearity: dispelling the myth'. Together they form a unique fingerprint.

Cite this