Geographically weighted regression and multicollinearity: dispelling the myth

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.

[1]  Martin Charlton,et al.  Living with Collinearity in Local Regression Models , 2012 .

[2]  J. Brian Gray,et al.  Introduction to Linear Regression Analysis , 2002, Technometrics.

[3]  R. O’Brien,et al.  A Caution Regarding Rules of Thumb for Variance Inflation Factors , 2007 .

[4]  Dennis M. Gorman,et al.  Quantifying geographic variations in associations between alcohol distribution and violence: a comparison of geographically weighted regression and spatially varying coefficient models , 2007 .

[5]  A. Fotheringham,et al.  The Multiple Testing Issue in Geographically Weighted Regression , 2016 .

[6]  Jennifer A. Miller,et al.  Spatial nonstationarity and the scale of species–environment relationships in the Mojave Desert, California, USA , 2011, Int. J. Geogr. Inf. Sci..

[7]  David C. Wheeler,et al.  Simultaneous Coefficient Penalization and Model Selection in Geographically Weighted Regression: The Geographically Weighted Lasso , 2009 .

[8]  A. Stewart Fotheringham,et al.  Geographical and Temporal Weighted Regression (GTWR) , 2015 .

[9]  Andrew O. Finley,et al.  Comparing spatially‐varying coefficients models for analysis of ecological data with non‐stationary and anisotropic residual dependence , 2011 .

[10]  Steven Farber,et al.  A Simulation-Based Study of Geographically Weighted Regression as a Method for Investigating Spatially Varying Relationships , 2011 .

[11]  Gordon F. Mulligan,et al.  Using Geographically Weighted Regression to Explore Local Crime Patterns , 2007 .

[12]  C. Bonferroni.  Il calcolo delle assicurazioni su gruppi di teste , 1935 .

[13]  A. Stewart Fotheringham.  Multicollinearity and Parameter Estimates in a Linear Model , 2010 .

[14]  Jayajit Chakraborty,et al.  Using geographically weighted regression for environmental justice analysis: Cumulative cancer risks from air toxics in Florida , 2011 .

[15]  John W. Tukey,et al.  Controlling Error in Multiple Comparisons, with Examples from State-to-State Differences in Educational Achievement , 1999 .

[16]  D. Wheeler.  Diagnostic Tools and a Remedial Method for Collinearity in Geographically Weighted Regression , 2007 .

[17]  David A. Belsley,et al.  Regression Analysis and its Application: A Data-Oriented Approach.@@@Applied Linear Regression.@@@Regression Diagnostics: Identifying Influential Data and Sources of Collinearity , 1981 .

[18]  A. Stewart Fotheringham,et al.  Local Forms of Spatial Analysis , 2010 .

[19]  David C. Wheeler.  Visualizing and Diagnosing Coefficients from Geographically Weighted Regression Models , 2010 .

[20]  David Wheeler,et al.  Multicollinearity and correlation among local regression coefficients in geographically weighted regression , 2005, J. Geogr. Syst..

[21]  Martin Charlton,et al.  Multiple Dependent Hypothesis Tests inGeographically Weighted Regression , 2009 .

[22]  Jammalamadaka.  Introduction to Linear Regression Analysis (3rd ed.) , 2003 .

[23]  David C. Wheeler,et al.  Comparing spatially varying coefficient models: a case study examining violent crime rates and their relationships to alcohol outlets and illegal drug arrests , 2009, J. Geogr. Syst..

[24]  David C. Wheeler,et al.  An assessment of coefficient accuracy in linear regression models with spatially varying coefficients , 2007, J. Geogr. Syst..

[25]  Scott Salzman,et al.  Assessment of Spatiotemporal Varying Relationships Between Rainfall, Land Cover and Surface Water Area Using Geographically Weighted Regression , 2012, Environmental Modeling & Assessment.

[26]  Fernando Tusell,et al.  Alleviating the effect of collinearity in geographically weighted regression , 2014, J. Geogr. Syst..