NCJ Number
17623
Date Published
1971
Length
78 pages
Annotation
STUDY OF TECHNIQUES FOR THE PREDICTION OF CRIME IN THE CITY OF LOS ANGELES CONDUCTED AS PART OF THE EVALUATION OF THE EFFECTIVENESS OF THE USE OF HELICOPTERS AS POLICE PATROL VEHICLES.
Abstract
THE OBJECTIVE OF THIS STUDY WAS TO PRODUCE A SET OF CRIME PREDICTIONS FOR USE IN COMPARISONS WITH ACTUAL CRIME OCCURRENCES. ALTERNATIVE APPROACHES TO CRIME PREDICTION (CAUSAL, QUASI-CAUSAL, ASSOCIATIVE, EXTRAPOLATIVE, AND PATTERN-RECOGNITION MODELS) ARE DISCUSSED, AS IS THE ENVIRONMENT WITHIN WHICH PREDICTIONS WERE DESIRED FOR THE IMMEDIATE APPLICATION. THE DECISION WAS MADE TO USE TIME-SERIES (EXTRAPOLATIVE) MODELS TO PRODUCE THE DESIRED PREDICTIONS. THE CHARACTERISTICS OF THE DATA AND THE PROCEDURE USED TO CHOOSE EQUATIONS FOR THE EXTRAPOLATIONS ARE DISCUSSED. THE USEFULNESS OF DIFFERENT FUNCTIONAL FORMS (CONSTANT, QUADRATIC, AND EXPONENTIAL FORMS) AND OF DIFFERENT PARAMETER ESTIMATION TECHNIQUES (MULTIPLE REGRESSION AND MULTIPLE EXPONENTIAL SMOOTHING) ARE COMPARED, AND THE QUALITY OF THE RESULTANT PREDICTIONS IS ASSESSED. APPENDIXES PRESENT A DISCUSSION OF THE DIFFERENT APPROACHES TO CRIME PREDICTION THAT WERE CONSIDERED, A TECHNIQUE FOR SIMULTANEOUS CONSIDERATION OF ARRESTS AND OFFENSES, AND ALGORITHMS FOR ANALYSIS OF TIME-SERIES. INCLUDED IS THE DEVELOPMENT OF A MODIFICATION TO THE MULTIPLE EXPONENTIAL SMOOTHING TECHNIQUE WHICH ELIMINATES THE NEED FOR A PRIORI ESTIMATES OF THE MODEL PARAMETERS. (AUTHOR ABSTRACT MODIFIED)