Spatial nonstationarity and property crime in Vancouver, Canada

Dr Martin Andresen1

1Griffith University, Southport, Australia

Spatial criminology, over the past 200 years, has consistently shown that there are spatial patterns in criminal activity. This research has been conducted at a variety of scales of analysis ranging from large sub-national units such as provinces or states to counties, neighbourhoods and, now, the micro-place, or street segment. Regardless of spatial scale, the relationships between crime and its covariates are most often modeled as spatially stationary processes; in other words, the relationships between covariates and crime are implicitly considered constant across space. Such regression models are referred to as global spatial regression because one (global) parameter for a covariate represents the change in crime (rates) for the entire study region. Though this may be the case in practice, such a global relationship is, fundamentally, an assumption. In this paper, I use geographically weighted regression (GWR) in the context of property crime in Vancouver, Canada, to investigate the temporal stability of these local relationships. The implications of these results are important for the theoretical understanding of spatial crime patterns but also in the context of criminal justice policy and crime prevention because previously thought global relationships may only be present in a few places leading to the misallocation of scarce public funds for theoretically-based interventions.


Biography:

Martin A. Andresen is an Associate Professor in the School of Criminology and Criminal Justice at Griffith University (Gold Coast). His research areas are in spatial crime analysis, crime and place, geography of crime, environmental criminology, and applied spatial statistics and geographical information analysis. Within these research areas he has published 3 edited volumes, 3 books, and more than 100 refereed journal articles and contributions to edited volumes. He is currently an Associate Editor for the Journal of Quantitative Criminology, an Affiliated Scholar in the Center for Evidence-Based Crime Policy at George Mason University, Chair of the Crime and Place Working Group in the Center for Evidence-Based Crime Policy at George Mason University, and an editorial board member for Journal of Quantitative Criminology, Journal of Criminal Justice, International Criminal Justice Review, Canadian Journal of Criminology and Criminal Justice, Social Sciences & Humanities Open, Methodological Innovations, and Criminology, Criminal Justice, Law & Society.