Spatio-temporal analysis of crime by developing a method to detect critical distances for the Knox test |
| |
Authors: | Mohsen Kalantari Bamshad Yaghmaei Somaye Ghezelbash |
| |
Institution: | 1. Department of Human Geography, Faculty of Geography, University of Tehran, Tehran, Iran;2. Department of Geography, University of Zanjan, Zanjan, Iran;3. Department of Remote Sensing and Geographical Information Systems, Tarbiat Modares University, Tehran, Iran;4. Department of Urban Geography, Shahid Beheshti University, Tehran, Iran |
| |
Abstract: | The present study examined and compared spatio–temporal interaction of the theft of car parts, shop burglary and motorcycle theft in the central business district (CBD) of the city of Zanjan in Iran. The Knox test was selected to detect spatio–temporal interaction. This test has been criticized as being subjective because the selection of critical distances is arbitrary; thus, a method is proposed to detect critical distances in the Knox test using the mean distance, natural breaks classification of nearest neighbour (NN) distance and Ripley’s k function. Results show obvious differences between the spatio-temporal clusters of the three sets of crimes. They also indicate that changing the spatial cut-offs within a cluster creates different temporal patterns. Of the three criteria for determining critical distances, NN classification based on natural breaks showed more interactions than the other methods. |
| |
Keywords: | Spatio-temporal analysis crime clustering Knox test |
|
|