Street-level spatial scan statistic and STAC for analysing street crime concentrations
Shiode, Shino (2011) Street-level spatial scan statistic and STAC for analysing street crime concentrations. Transactions in GIS 15 (3), pp. 365-383. ISSN 1361-1682.
This study develops new types of hotspot detection methods to describe the micro-space variation of the locations of crime incidents at the street level. It expands on two of the most widely used hotspot detection methods, Spatial and Temporal Analysis of Crime and Spatial Scan Statistic, and applies them to the analysis of the network space. The study first describes the conceptual and the methodological framework of the new methods followed by analyses using: (1) a simulated distribution of points along the street network; and (2) real street-crime incident data. The simulation study using simulated point distributions confirms that the proposed methods is more accurate, stable and sensitive in detecting street-level hotspots than their conventional counterparts are. The empirical analysis with real crime data focuses on the distribution of the drug markets and robberies in downtown Buffalo, NY in 1995 and 1996. The drug markets are found to form hotspots that are dense, compact and stable whereas hotspots of the robberies are observed more thinly across a wider area. The study also reveals that the location of the highest risk remains on the same spot over time for both types of crimes, indicating the presence of hotbeds which requires further attention.
|School:||Birkbeck Schools and Departments > School of Social Sciences, History and Philosophy > Geography, Environment and Development Studies|
|Depositing User:||Shino Shiode|
|Date Deposited:||25 Jun 2012 07:25|
|Last Modified:||17 Apr 2013 12:23|
Additional statistics are available via IRStats2.