skip to primary navigation skip to content
 

Urban crime pattern analysis in Sheffield

Urban crime pattern analysis in Sheffield

Research Team: M. Craglia, R. Haining, P. Wiles

Abstract

The increased availability of digital data and the increased scrutiny of public expenditure are opening new opportunities for detailed spatial analysis of social behaviour and policy initiatives to target resources where they are most needed. Two such policy areas in which the use of GIS combined with spatial analysis tools has made significant progress are health and police services, which are at the top of the political agenda due to increasing `demand' and spiralling costs. Against this background, this paper presents the results of a collaborative research project carried out in Sheffield on the use of GIS for crime pattern analysis. The research described is significant in a number of respects: it is based on high-quality detailed crime data and geographical data for the whole of Sheffield; it compares two different methodologies for crime pattern analysis, one developed specifically for crime, the other for health research; and it demonstrates the policy value of this transfer of methodologies across disciplines.

Clusters of crime in Sheffield, UK, were identified using the following two packages that employ two different methods of cluster detection. Their results were compared. (Craglia et al., 2000).

  1. Spatial and Temporal Analysis of Crime (STAC) package developed by the Illinois Criminal Justice Information Authority.
  2. SAGE, a linked windows software environment, which tightly couples Arc/Info with a suite of statistical (including spatial statistical) techniques ((Haining 1996). SAGE implements a number of techniques routinely used in spatial epidemiology to analyse the relative risk of disease.

Illustrations

Image as described adjacent

Figure 1: Comparison of STAC and Getis-Ord clusters at 550 metres.

Image as described adjacent

Figure 2: Bayes-adjusted standardised burglary rates.

Image as described adjacent

Figure 3: Townsend-adjusted standardised burglary rates.

Further reading

  • Craglia, M., Haining, R. and Wiles, P. (2000). "A comparative evaluation of approaches to urban crime pattern analysis." Urban Studies 37(4): 711-729.
  • Haining, R., Ma, J. and Wise, S.W. (1996). "Design of a software system for interactive spatial statistical analysis linked to a GIS." Computational Statistics 11: 449-466.
  • Sheffield Centre for Geographic Information and Spatial Analysis