skip navigation


Register for Latest Research

Stay Informed
Register with NCJRS to receive NCJRS's biweekly e-newsletter JUSTINFO and additional periodic emails from NCJRS and the NCJRS federal sponsors that highlight the latest research published or sponsored by the Office of Justice Programs.

NCJRS Abstract

The document referenced below is part of the NCJRS Virtual Library collection. To conduct further searches of the collection, visit the Virtual Library. See the Obtain Documents page for direction on how to access resources online, via mail, through interlibrary loans, or in a local library.


NCJ Number: 76887 Find in a Library
Title: Forecasting Crime Rates - A Review of the Available Methodology
Author(s): D Weller
Corporate Author: Hoover Institution
Ctr for Econometric Studies of the Justice System
Stanford University
United States of America
Date Published: 1979
Page Count: 26
Sponsoring Agency: Hoover Institution
Stanford, CA 94305
National Institute of Justice/
Rockville, MD 20849
US Dept of Justice

US Dept of Justice NIJ Pub
Washington, DC 20531
Grant Number: 77-NI-99-0071
Publication Number: CERDCR-4-79
Sale Source: National Institute of Justice/
NCJRS paper reproduction
Box 6000, Dept F
Rockville, MD 20849
United States of America
Document: PDF
Type: Best Practice/State-of-the-Art Review
Language: English
Country: United States of America
Annotation: This paper discusses issues involved in forecasting the incidence of crime, a variety of approaches which might be used to produce crime forecasts, and the literature dealing with methods that have been used; recommended research is highlighted.
Abstract: Although criminal justice researchers have devoted more effort to the testing of hypotheses concerning determinants of crime than they have to the prediction of future crime rates, forecasting models can be of service to criminal justice planners in a number of ways. The most straightforward approach to forecasting is to project the value of the crime rate into future periods by extrapolation from its values in prior periods. Techniques employed for this univariate approach include moving average, regression, and the Box-Jenkins technique. The primary disadvantage of this approach is that it has no behavioral content. A second approach, indicator tracking, addresses the underlying determinants of the crime rate, i.e., social or economic factors. Techniques employed with this approach include the multiple regression analysis, and Delphi techniques. System flow models and microsimulation draw upon the techniques of operations research to investigate the interactions of different elements in the criminal justice system. Perhaps the most promising approach to overcoming the limitations of the multiple regression models is the combination of several regression equations into a simultaneous system; each equation is used to specify the hypothesized behavior of one part of the system, e.g., the effect of police expenditures on arrest rates. Based upon review of the available approaches and techniques for the forecasting of crime, it is concluded that extrapolation by means of one of the univariate methods would be most appropriate for generating short-term forecasts at a reasonable cost. As the time horizon over which the forecast is to be made increases, so do the dangers of pure extrapolation. The use of a coherent theoretical model offers the possibility of long-term forecasts in approximate terms, and research activities should focus on its development. Such a model might include the definition and measurement of the risks and returns of crime for individuals according to specific characteristics; investigation of the risks and returns of alternative activities, such as legal employment; and investigation of social and environmental variables which might account for preferences with respect to legal and illegal activity. One table, 4 notes, and 27 references are included.
Index Term(s): Crime prediction; Estimated crime incidence; Estimating methods; Modeling techniques; Technical assistance reports
Note: Technical report.
To cite this abstract, use the following link:

*A link to the full-text document is provided whenever possible. For documents not available online, a link to the publisher's website is provided. Tell us how you use the NCJRS Library and Abstracts Database - send us your feedback.