Abstract
Analyses of criminals' travel patterns can provide significant suggestions to improve crime management. This study extends the investigation of criminals' travel behavior from journey-to-crime to journey-after-crime. Moreover, new methods are developed to examine the spatial patterns of location pairs when restricted by the underlying geographical process. The methods are employed to investigate criminals' journey-after-auto-theft in the city of Buffalo, New York. The analyses reveal that auto thieves' trips from vehicle-theft locations to the corresponding vehicle-recovery locations are local in nature. The travel distances are significantly shorter than the randomly simulated trips; the travel directions are biased from the random directions as well.
Notes
1 Details about the distributions of both the observation and the estimation are available from the author upon request.
2 Details about the algorithm, the distributions of the actual and simulated trips, and their means are available from the author upon request.
3 Details about the algorithm, the distributions of the directions of the actual and simulated trips, and the calculation of the average directions are available from the author upon request.
* I would like to thank Dr. Hugh Calkins and Dr. Peter Rogerson for the discussions during the early stage of forming the research idea. I also want to extend my appreciation to the anonymous referees and to Mr. Joe Morgan for their insightful comments on the article.