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

STOCHASTIC MODELS OF CRIME RATES

NCJ Number
59344
Journal
International Journal of Comparative and Applied Criminal Justice Volume: 2 Issue: 2 Dated: (WINTER 1978) Pages: 127-151
Author(s)
S J DEUTSCH
Date Published
1978
Length
25 pages
Annotation
A METHODOLOGY FOR MODELING AND PROJECTING THE INCIDENCE OF CRIME THROUGH PAST OCCURRENCES IS ILLUSTRATED; RESULTS OF THE MODELING PROCEDURES FOR 10 MAJOR METROPOLITAN CITIES ARE PRESENTED.
Abstract
THE GENERAL MODEL CLASS UTILIZED IS THE MULTIPLICATIVE AUTOREGRESSIVE-MOVING AVERAGE MODEL; BUILDING OF AN APPROPRIATE EMPIRICAL-STOCHASTIC MODEL IS ACCOMPLISHED BY 3-STAGE ITERATIVE PROCEDURE OF IDENTIFICATION, ESTIMATION, AND DIAGNOSTIC CHECKING. DATA UTILIZED IN THE MODELING EFFORTS IS THAT OBTAINED FROM THE FEDERAL BUREAU OF INVESTIGATION REPORTS, RETURN A WHICH DESCRIBES STATISTICS OF MONTHLY OCCURRENCE OF THE SEVEN INDEX CRIMES INCLUDING HOMICIDE, FORCIBLE RAPE, ROBBERY, BURGLARY, ASSAULT, LARCENY, AND VEHICLE THEFT. THE COLUMN DELINEATING 'NUMBER OF ACTUAL OFFENSES' WAS UTILIZED. DATA WAS COLLECTED PRIMARILY FROM 1966 TO 1975 FOR THE CITIES OF ST. LOUIS, MO.; DALLAS, TEX.; PORTLAND, OREG.; CINCINNATI, OHIO; LOS ANGELES, CALIF.; KANSAS CITY, MO.; ATLANTA, GA.; CLEVELAND, OHIO; BOSTON, MASS.; AND DENVER, COLO. THE TENTATIVE MODEL FORM AND ANY REFINEMENTS TO IT RESULTING FROM THE ITERATIVE MODEL BUILDING PROCEDURES ARE A DIRECT CONSEQUENCE OF THE INFORMATION OR STRUCTURE CONTAINED IN THE DATA. THEREFORE, THE FINAL MODEL FORMS ARE NOT BIASED BY THE INDIVIDUAL MODELER'S A PRIORI KNOWLEDGE OF THE SYSTEM UNDER STUDY. ANALYSIS OF THE FORECASTING EFFICIENCY OF THE DEVELOPED MODELS REVEALED AN ACCURACY RATE IN EXCESS OF 90 PERCENT. IT WAS ALSO NOTED THAT UNIFORM CRIME REPORT DATA, REGARDLESS OF POTENTIAL DIFFERENCES IN LOCAL REPORTING PRACTICES, APPEARS TO HAVE CONSISTENT INFORMATION CONTENT. IN ADDITION, THERE APPEARS TO BE A FUNDAMENTAL CAUSAL MECHANISM WHICH GIVES RISE TO THE OCCURRENCE OF CRIMES BY CATEGORY. FINALLY, THE PARAMETER VALUES WITHIN CRIME TYPE CATEGORIES ELUCIDATE DIFFERENCES AND SIMILARITIES IN THE OCCURRENCE OF CRIME IN THE GEOGRAPHIC AREA STUDIED. STATISTICAL TABULAR DATA, FORMULAS AND GRAPHS COMPRISE THE BULK OF THE DOCUMENT; REFERENCES ARE INCLUDED. (LWM)