Estimating the Causal Effect of Gun Prevalence on Homicide Rates: A Local Average Treatment Effect Approach

59 Pages Posted: 14 Jul 2008

See all articles by Tomislav Victor Kovandzic

Tomislav Victor Kovandzic

University of Alabama at Birmingham - Department of Justice Sciences

Mark E. Schaffer

Heriot-Watt University - Centre for Economic Reform and Transformation; Centre for Economic Policy Research (CEPR); IZA Institute of Labor Economics

Gary Kleck

Florida State University - College of Criminology and Criminal Justice

Abstract

This paper uses a "local average treatment effect" (LATE) framework in an attempt to disentangle the separate effects of criminal and noncriminal gun prevalence on violence rates. We first show that a number of previous studies have failed to properly address the problems of endogeneity, proxy validity, or heterogeneity in criminality. We demonstrate that the time series proxy problem is severe; previous panel data studies have used proxies that are essentially uncorrelated in time series with direct measures of gun relevance. We adopt instead a cross-section approach: we use U.S. county-level data for 1990, and we proxy gun prevalence levels by the percent of suicides committed with guns, which recent research indicates is the best measure of gun levels for cross-sectional research. We instrument gun levels with three plausibly exogenous instruments: subscriptions to outdoor sports magazines, voting preferences in the 1988 Presidential election, and numbers of military veterans. In our LATE framework, the estimated impact of gun prevalence is a weighted average of a possibly negative impact of noncriminal gun prevalence on homicide and a presumed positive impact of criminal gun prevalence. We find evidence of a significant negative impact, and interpret it as primarily "local to noncriminals", i.e., primarily determined by a negative deterrent effect of noncriminal gun prevalence. The beneficiaries of the reduced level of violence may include substantial numbers of (urban) criminals, the murders of whom decrease via spillovers from noncriminal gun prevalence.

Keywords: crime, homicide, gun levels, endogeneity

JEL Classification: K42, C51, C52

Suggested Citation

Kovandzic, Tomislav Victor and Schaffer, Mark E. and Kleck, Gary, Estimating the Causal Effect of Gun Prevalence on Homicide Rates: A Local Average Treatment Effect Approach. IZA Discussion Paper No. 3589. Available at SSRN: https://ssrn.com/abstract=1158985 or http://dx.doi.org/10.1111/j.0042-7092.2007.00700.x

Tomislav Victor Kovandzic (Contact Author)

University of Alabama at Birmingham - Department of Justice Sciences ( email )

OB15 101
1530 3rd Avenue South
Birmingham, AL 35294
United States
205-934-0668 (Phone)
205-934-2067 (Fax)

Mark E. Schaffer

Heriot-Watt University - Centre for Economic Reform and Transformation ( email )

School of Management - Department of Economics
Edinburgh EH14 4AS
United Kingdom
+44 131 451 3494 (Phone)
+44 131 451 3008 (Fax)

HOME PAGE: http://www.hw.ac.uk/ecoWWW/cert

Centre for Economic Policy Research (CEPR)

London
United Kingdom

IZA Institute of Labor Economics

P.O. Box 7240
Bonn, D-53072
Germany

Gary Kleck

Florida State University - College of Criminology and Criminal Justice ( email )

Eppes Hall
112 S. Copeland Street
Tallahasse, FL 32306-1206
United States

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
94
Abstract Views
828
rank
286,042
PlumX Metrics