An interactive detector for spatial associations

ABSTRACT

Geographical variables are usually not independent of each other. Hence, it is necessary to investigate the effect of interactions among explanatory variables on a response variable to characterize spatially enhanced or weakened relationships among all variables. The geographical detector (GD) model identifies zones for each explanatory variable, divides the study area into spatial units by overlapping these zones, and quantifies spatial associations as the power of interactive determinant (PID) between a response variable and explanatory variables. Consequently, the PID values depend upon the distributions of explanatory variables (i.e. spatial characteristics) and the subsequent division of spatial units out of these explanatory variables. This study has therefore proposed an Interactive Detector for Spatial Associations (IDSA) to optimize spatial division and improve PID. IDSA utilizes spatial autocorrelation of each explanatory variable and optimizes spatial units based on spatial fuzzy overlay to compute PID. We test the IDSA on both a simulation study and practical case that analyzes road deterioration in Australia. Results showed that the IDSA model could effectively assess the PID while existing GD overestimated PID. Hence, the IDSA improves the GD with refined spatial units based on explanatory variables to enhance their local spatial associations with a response variable.

KEYWORDS:

• Interaction effect
• spatial association
• geographical detector
• spatial fuzzy overlay
• spatial heterogeneity

Acknowledgments

We would like to thank Qindong Li, Brett Belstead and Tom McHugh from Main Roads Western Australia, Government of Western Australia, for providing their practical knowledge in road surface performance data application, practical decision making and policies development for road infrastructure asset management. We would like to thank Prof. May Yuan and anonymous reviewers for their constructive suggestion and comments for improving this manuscript.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data and codes availability statement

The simulation data and codes that support the findings of this study are available with a DOI at http://doi.org/10.6084/m9.figshare.13636157. The model code can be run in R using ‘model.R’ with the simulation dataset ‘simdata.rda’. Data and codes used to create each figure are presented in the file ‘Data and codes.pdf’, where data of Figures 2, Figure3 and Figure4 are computed with the simulation dataset ‘simdata.rda’, data of Figures 6, Figure7, Figure9, Figure11 and Figure 12 are presented in ‘data.figure6.rda’, ‘data.figure7.rda’, ‘data.figure9.rda’, ‘data.figure11.rda’ and ‘data.figure12.rda’, respectively, and data of other figures are listed in tables in the file ‘Data and codes.pdf’. The raw road deterioration performance data that support the practical experiment of this study were provided by Main Roads Western Australia and cannot be made publicly due to data use restrictions.

Additional information

Funding

This research was supported by the Australian Government through the Australian Research Council’s Discovery Early Career Researcher Award funding scheme (Project No. DE170101502) and Discovery Project (Project No. DP180104026).

Notes on contributors

Yongze Song

Yongze Song is a Lecturer at Curtin University, Australia, and a Fellow of the Royal Geographical Society (with IBG), United Kingdom. His current research interests include geospatial analysis methods, spatial statistics, sustainable development, and infrastructure management.

Peng Wu

Peng Wu is a Professor at Curtin University, Australia, and an Australian Research Council (ARC) DECRA Fellow. His research interests include sustainable construction, lean production and construction, production and operations management, and life cycle assessment.