This is the third of eight chapters on "Crime Travel Demand Modeling" from the user manual for CrimeStat IV, a spatial statistics package that can analyze crime incident location data.
This chapter, "Trip Generation Modeling." explains the theory and mechanics of the trip-generation stage. "Trip generation" is a "model of the number of trips that originate and end in each zone for a given jurisdiction." Given a set of destination zones ("N") and origin zones ("M") - which include all the destination zones and possibly zones from adjacent jurisdictions - separate models are provided of the number of crimes originating and ending in each of these zones. These are called a "crime production" model and "a crime attraction" model. Because the models are predictions, there is always error between the actual number and that predicted. It is best viewed as a "proxy model" in which the variables are proxies for conditions that are generating crimes, either in terms of environments that produce offenders or in terms of locations that attract offenders. So long as the error is not too large, the models can be used for both analyzing the correlates of crime for forecasting or for simulating policy interventions. This chapter first discusses the logic underlying trip generation modeling, including the calibration of a model, the addition of external trips in making a model, and the balancing of predicted origins and predicted destinations. The mechanics of conducting the trip generation model with CrimeStat is then discussed and illustrated with data from Baltimore County. 9 tables, 11 figures, and 39 references