A Micro-Spatial Longitudinal Analysis of Home Burglary Concentration and Spatial Stability in the Context of a Crime Drop

Abstract

We examine the spatial concentration and spatial stability of home burglary (N=46,684) on street segments (N=26,875) in the context of a substantial city-level burglary drop from 2005 to 2014 in Antwerp, Belgium. Longitudinal trends in spatial concentrations of burglary are considered using descriptive statistics, generalized Gini coefficients, local Getis-Ord statistics, and a longitudinal extension of Andresen’s non-parametric spatial point pattern test (SPPT). Home burglary is substantially concentrated on street segments. Burglary point patterns exhibit a moderate to high degree of spatial stability over time. About 87% of street segments with burglary experienced a net decrease in crime and less than 2% of street segments with burglary experienced a net increase. The citywide home burglary drop manifested itself rather uniformly across street segments and the majority of street segments that experienced burglary contributed relatively equally to the crime drop. In other words, we do not find strong evidence that the city-level crime drop can be tied to substantial decreases in a few specific places, nor do we find that the reductions in burglary are spatially concentrated.

Wouter Steenbeek

Senior Researcher

My research interests include spatio-temporal patterns of crime, offender decision-making, neighborhoods, machine learning, and R.