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

Quickguide to CrimeStat IV (CrimeStat IV: A Spatial Statistics Program for the Analysis of Crime Incident Locations, Version 4.0)

NCJ Number
242962
Author(s)
Ned Levine
Date Published
June 2013
Length
221 pages
Annotation

This second chapter of the manual for Crime Stat IV - a spatial statistics package that can analyze crime incident location data - contains brief instructions for the use of CrimeStat IV.

Abstract

The program contains 5 basic groupings in 27 program tabs and 1 option tab. Each tab lists routines options and parameters. The data-setup section consists of defining the dataset and variables for a primary file (required) and a secondary file (optional); identifying a reference grid; and defining measurement parameters. The "spatial description" section calculates spatial description, spatial autocorrelation, distance analysis, and "hot spot" statistics. The spatial autocorrelation indices identify whether point locations are spatially related, either clustered or dispersed. These indices would typically be applied to zonal data where an attribute value can be assigned to each zone; six spatial autocorrelation indices are calculated. "Hot spot" (or cluster) analysis identifies groups of incidents that are clustered together. It is a method of second-order analysis that identifies the cluster membership of points. There are a number of different hot-spot analysis routines. They are organized on three program tabs: Hot-Spot Analysis I, Hot-Spot Analysis II, and Hot-Spot Analysis of Zones. The first spatial modeling section conducts kernel density estimation, "Head Bang" statistics, space-time analysis, journey-to-crime calibration and estimation, and Bayesian journey-to-crime diagnostics and estimation. The spatial modeling section is composed of five distinct tabs. The second spatial modeling section conducts regression modeling of a dependent variable, either binomial, unconstrained, or a count variable. It also includes a module for modeling discrete (nominal) choices. The crime-travel-demand module is a sequential model of crime travel by zone over a metropolitan area. Crime incidents are allocated to zones, both by the location where the crime occurred and the location where the offender started. Extensive figures of computer screens