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

• NCJ Number: 242960
• Author(s): Ned Levine
• Date Published: June 2013
• Length: 1798 pages
• Grant Number(s): 2005-IJ-CX-K037
• Agencies: NIJ-Sponsored
• Publication Type: Technical Assistance; Instructional Material (Programmed)

Annotation

This is the full-text user manual for "CrimeStat IV," a spatial statistics package that can analyze crime incident location data.

Abstract

The purpose of CrimeStat IV is to provide a variety of tools for the spatial analysis of crime incidents or other point locations. It is a stand-alone "Windows" program that can interface with most desktop geographic information systems (GIS). It is designed to operate with large crime-incident data sets collected by metropolitan police departments; however, it can also be used for other types of applications that involve point locations, such as the location of arrests, motor vehicle crashes, emergency medical service pickups, or various types of facilities. The manual details the program step-by-step, describing how it can be used by a crime mapping/analysis unit within a police department. Chapter 2 provides a quick guide for all the data definition and program routines, and Chapter 3 provides detailed instructions on setting up data to run with CrimeStat IV. The statistical routines are described in parts II, III, IV, V, and VI. Part II presents a number of statistics for spatial description. Part III presents "hot spot" analysis techniques for both points and zones. Part IV presents a number of statistics for spatial modeling (called Spatial Modeling I), and Part V presents multivariate tools for spatial modeling (called Spatial Modeling II). Finally, Part VI presents a crime travel demand module. The different statistics are presented, and detailed examples of each technique are shown. After listing CrimeStat IV references, appendixes provide notes on the statistical comparison of two samples, Ordinary Least Squares and Poisson Regression models, and Negative Binomial Regression models and estimation methods.