Australian Institute of Criminology

Skip to content

Finding a serial burglar's home using distance decay and conditional origin-destination patterns: A test of empirical Bayes journey-to-crime estimation in The Hague

74 Leichhardt Street, Griffith, ACT
08 December 2008

Professor Richard Block
Loyola University Chicago

Presentation overview

Can we identify where an offender lives by his or her crimes' locations? Journey-to-crime estimation uses crime locations to locate a serial offender's home. In this presentation, we test a new method: empirical Bayes journey-to-crime estimation. It uses an origin-destination rule as well as the distance-decay rule of prior methods. The profiler asks not only what distances previous offenders travelled between their home and the crime scenes but also where previous offenders lived who offended at the locations included in the present crime series. Using CrimeStat 3.1, we apply the new method to 62 serial burglars in The Hague, The Netherlands, with higher predictive accuracy than methods using only a distance-decay rule, and improving also the search for marauders. After applying the method to prediction of a specific burglar, we discuss its limitations and offer suggestions for its future development..

The presenter

Richard Block, PhD, Professor Emeritus of Sociology and Criminal Justice at Loyola University Chicago, has been studying the relationship between crime and community for the last 30 years. His first study of the geographic distribution of crime was published in 1977. Widely recognized for his work in the development of geographic information systems (GIS) for crime analysis and database management, he helped develop the ICAM computer-mapping facility of the Chicago Police Department and has advised many other departments on computer mapping and crime-pattern spatial analysis. He is currently researching space and place characteristics, such as rapid-transit stations and specific housing complexes, that increase the risk of crime; distance travelled by offender and victim in incidents of violent crime; prediction of the anchor point of serial offenders; and use of GIS techniques in studying environmental stressors related to breast cancer. He is a co-developer of CrimeStat 2 and 3 and has given short courses on CrimeStat in the U.S., Canada, England and the Netherlands.