Spatial pattern of motor vehicle thefts in Ciudad Juárez, Mexico: an analysis using geographically weighted Poisson regression

Abstract

Most Latin American cities have been experiencing a rise in criminality and Ciudad Juarez is not the exception. The aim of this paper is to examine the spatial heterogeneity of factors influencing motor vehicle theft (MVT) in Ciudad Juarez, Mexico. Starting in 2007, the city experienced a rise in crimes, such as motor vehicle theft, which peaked at 9,109 in 2011 and has since decreased to 2,826 in 2014. The data used for this analysis includes criminal warrants of motor vehicle theft provided by Chihuahua’s State Police (2014) and the socioeconomic and demographic variables were provided by the Housing and Population Census (2010), all of them at census tract level. The methodology used Generalized Linear Model (GLM) Poisson and an extension of it called geographically weighted Poisson regression (GWPR). The paper identifies some variables that behave different to the predictions of environmental criminology theories in developed countries.