Quarters and Crime: Forecasting the Occurrence of Crime at the Block Level in Three Month Intervals

Marc L. Swatt, Northeastern University
Denn (Dennis W.) Roncek, University of Nebraska at Omaha

ABSTRACT
The purpose of this presentation is to develop a theoretically driven model for predicting the reoccurrence of a particular crime type on a city block at a three month time interval. This research will expand upon the "Same Place, Next Year" logistic regression technique described in Roncek (1987). Additional data sources such as Census data, assessors data, probation and parole data, and 911 calls for service data will be used to create a predictive model for police reports of Part I crimes for a medium-sized Midwestern city. These predictive models will then be compared to the actual levels of criminal activity. Police implications will also be discussed.

(Return to Program Resources)

Updated 05/20/2006