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

Creating a UCR Utility

NCJ Number
215341
Author(s)
Michael D. Maltz; Harald E. Weiss
Date Published
June 2006
Length
21 pages
Annotation
This paper describes the process of cleaning the data found in the Federal Bureau of Investigation’s (FBI’s) Uniform Crime Reports (UCR) in order to present a usable version of the crime data for the criminal justice community.
Abstract
Four deliverable items were provided to the National Institute of Justice (NIJ) as the work product of this grant: (1) cleaned UCR data for the 50 States and the District of Columbia; (2) a UCR charting utility to allow users to plot monthly crime data; (3) a set of instructions to allow the addition of subsequent years of data; and (4) an analysis of the nature and extent of “missingness” in the UCR data. The UCR is a collection of crime data from law enforcement agencies around the country that voluntarily report their crime data. Although the UCR has undergone major revisions during its lifetime, problems with the data persist, including missing data and misreporting problems. The researchers describe obtaining and organizing the UCR data, which involved combining the data from annual files into longitudinal files running from January 1960 to December 2002. Types of data extracted are described and include monthly crime counts for the seven index crimes, population counts, county indicators, and population groups. The data cleaning process was largely automatic and was accomplished through the use of a set of macros that enabled depictions of a time series for each crime category, which highlighted needed changes. Each of the macros is described, followed by a description of the “fine tuning” of the data, which included a consideration of the multiple agencies submitting UCR data. Explanations about the clean UCR dataset, which is housed in Excel workbooks, and procedures for incorporating additional year’s data are offered. Three tasks are identified that will make future revisions of the UCR data more effective: (1) develop imputation methods to account for missing data; (2) combine individual Originating Agency Identifiers to permit the calculation of countrywide crime data; and (3) identify anomalies in the crime subcategories. Table, exhibit, footnotes, references