skip navigation

CrimeSolutions.gov

Add your conference to our Justice Events calendar

PUBLICATIONS

NCJRS Abstract

The document referenced below is part of the NCJRS Library collection.
To conduct further searches of the collection, visit the NCJRS Abstracts Database.

How to Obtain Documents
 
NCJ Number: NCJ 202974   Add to Shopping cart   Find in a Library
Title: Detection and Prediction of Geographic Change in Crime Rates: Final Report
Author(s): Peter Rogerson ; Rajan Batta ; Christopher Rump ; Alok Baveja
Corporate Author: New York State University at Buffalo
United States of America
Date Published: 2003
Page Count: 151
Sponsoring Agency: National Institute of Justice
US Department of Justice
Office of Justice Programs
United States of America
Grant Number: 98-IJ-CX-K008
Sale Source: NCJRS Photocopy Services
Box 6000
Rockville, MD 20849-6000
United States of America

New York State University at Buffalo
Buffalo Criminal Law Review
605 John Lord O'Brian Hall
Armherst Campus
Armherst, NY 14260
United States of America
Document: PDF 
Type: Report (Study/Research)
Language: English
Country: United States of America
Annotation: This is the final report of a study that developed statistical methods and monitoring models for the quick detection of emerging and declining geographic clusters of criminal activity; a second related objective was to develop prediction models that forecast crime patterns (geographic displacement) in response to the deployment of resources.
Abstract: A common problem in the study of geographic patterns is the determination of whether there are local subregions that exhibit significantly high or low values on some variable of interest. The focus of this study was the detection of clusters of criminal activity that occur in relation to some pre-existing expectations (e.g., previous year’s data). The study also focused on the monitoring of crime data as soon as it becomes available, such that changes in geographic crime patterns can be detected as quickly as possible. The first chapter of the report describes a statistical method that was developed to assess the significance of geographic clustering, with crime analysis as an intended application. The method provides a way to assess the significance of the maximum of a set of local statistics, and may be viewed as a method that allows for the assessment of the statistical significance of a kernel-based, smooth surface. The method is similar in concept to scan statistics, in that it considers many possible subregions and evaluates the statistical significance of the most extreme value. In addition, the method yields a calculable critical value that may be derived without resorting to Monte Carlo simulation methods. The second chapter of the report describes a new procedure for detecting changes over time in the spatial pattern of point events, combining the nearest neighbor index and cumulative sum methods. The method results in the rapid detection of deviations from expected geographic patterns. The method may be used for various subregions of the study area, and it may be implemented using time windows of differing length to search for changes in spatial pattern that may occur at particular time scales. The method does not answer the question of why the change in pattern has occurred, but it does provide a way of signaling when a significant spatial change occurred. This should lead to better short-term strategic plans and further hypotheses and investigations regarding the cause of the change. The system is intended to complement, rather than replace, other methods of crime analysis. The third chapter of this report presents the details of the researchers’ socioeconomic model of geographical displacement and spatial concentration of crime. It notes that there is mounting evidence that earlier assumptions about the displacement of crimes to other locations bordering the targeted geographic area may have been over stated. At the same time, there is increasing evidence of diffusion effects, whereby the benefits of enforcement policies in one area spread to other areas. The researchers studied particular police departments’ situation and used their data to develop an appropriately structured model for crime analysis. Details of the research are presented in chapter 4. The two departments studied were in Camden, NJ, and Philadelphia, PA. The micro-level component of the research developed a sequential decisionmaking model for assisting law enforcement officials in allocating resources during a crackdown operation on illicit drug markets. Results showed that using maximum enforcement for a significant number of days during a crackdown might be optimal in neighborhoods with a severe drug problem. A cyclical crackdown-back off strategy may be optimal where residual deterrence dominates financial hardship. For all markets, a much quicker and less costly effort could be implemented if the daily enforcement intensity is increased. The model also provides guidelines for identifying markets where crackdowns would be ineffective in eliminating a drug market. This report also provides brief descriptions of the various contributions made by this research. References, tables, figures, and appendices
Main Term(s): Crime Statistics ; Models
Index Term(s): Statistical analysis ; Prediction ; Statistics ; Crime prediction ; Impact prediction ; NIJ grant-related documents
Note: See NCJ-202933 for the Executive Summary.
   
  To cite this abstract, use the following link:
https://www.ncjrs.gov/App/Publications/abstract.aspx?ID=202974

* A link to the full-text document is provided whenever possible. For documents not available online, a link to the publisher's web site is provided.