U.S. flag

An official website of the United States government, Department of Justice.

NCJRS Virtual Library

The Virtual Library houses over 235,000 criminal justice resources, including all known OJP works.
Click here to search the NCJRS Virtual Library

Predicting Criminals' Targets

NCJ Number
180838
Journal
Crime Prevention and Community Safety: An International Journal Volume: 1 Issue: 4 Dated: 1999 Pages: 7-13
Author(s)
Timothy R. Wheeler
Date Published
1999
Length
7 pages
Annotation
In Great Britain, Post Office Counters Ltd (POCL), which operates the nationwide network of post offices, uses a risk index to identify which of its offices are most at risk for crime and thereby warrant priority for security upgrading; this paper describes the index used and its sensitivity in identifying priorities.
Abstract
In 1998-99 the POCL experienced 789 robberies and 642 burglaries. The research commissioned for the development of the risk index began with a statistical analysis of 31 possible factors and a detailed analysis of the most promising factors. Eight factors were found to have an impact: insurance category; region; office type; official location type; catchment area class, which provides information on the inhabitants living in the surrounding area; motorway access (the distance to the nearest motorway junction); business volume; and the proportion of business volume from pensions, allowances, and benefits transactions. The model used employs the linear regression technique and shows the relationship between robberies and office characteristics. In showing the relative importance of the model factors, the model allows the ranking of offices according to their relative risk of crime. The index still only explains a small proportion of the "logic" in office choice for robbery, but its predictive capability is better than most such models. Security investments are being allocated based on the calculations of the model and the risk rankings for the offices. 4 tables and 6 notes