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

Systematic Measurement Error with State-Level Crime Data: Evidence From the "More Guns, Less Crime" Debate

NCJ Number
209565
Journal
Research in Crime and Delinquency Volume: 42 Issue: 2 Dated: May 2005 Pages: 187-210
Author(s)
Robert A. Martin Jr.; Richard L. Legault
Date Published
May 2005
Length
24 pages
Annotation
This study critically analyzed the State-level data used in the book, "More Guns, Less Crime" (MGLC).
Abstract
In analyzing the effects on crime of laws that allow citizens permits to carry concealed weapons (CCW), MGLC used the Uniform Crime Reports' (UCR) "Crime by County" cross-sectional time-series data. The integrity of the State-level data used by MGLC has yet to be examined, even though numerous research studies related to the gun-control debate continue to perform increasingly complex analyses that draw contradictory conclusions and inferences from those data. In addition to performing such an analysis, the current study also adds to the literature by using data other than the MGLC data to examine the effects of CCW law on State-level crime rates. Preliminary analyses of State-level MGLC data consisted of comparing these data to State-level UCR annual time-series data available online in the spreadsheet format from the Bureau of Justice Statistics, which are presented as provided by the FBI without manipulation. Differences in the data sources are shown in how crime counts and population estimates are obtained, which influences parameter estimates when used in complex analyses. Using the UCR data, which are judged by the authors to be more reliable than the MGLC data, this study concludes that the majority of the MGLC State-level findings are mere artifacts of reporting error and data anomalies. Thus, any inferences drawn from the MGLC State-level data are seriously flawed. The data deemed more reliable in the current study indicate that for most offenses, the effects of CCW laws are eliminated and for other offenses are significantly moderated. 7 tables, 36 notes, and 28 references