Police, Crime and the Problem of Weak Instruments: Revisiting the “More Police, Less Crime” Thesis

Tomislav V. Kovandzic, Mark E. Schaffer, Lynne M. Vieraitis, Erin A. Orrick, Alex R. Piquero

Research output: Contribution to journalArticle

Abstract

Objectives
A key question in the general deterrence literature has been the extent to which the police reduce crime. Definitive answers to this statement, however, are difficult to come by because while more police may reduce crime, higher crime rates may also increase police levels, by triggering the hiring of more police. One way to help overcome this problem is through the use of instrumental variables (IV). Levitt, for example, has employed instrumental variables regression procedures, using mayoral and gubernatorial election cycles and firefighter hiring as instruments for police strength, to address the potential endogeneity of police levels in structural equations of crime due to simultaneity bias.
Methods
We assess the validity and reliability of the instruments used by Levitt for police hiring using recently-developed specification tests for instruments. We apply these tests to both Levitt’s original panel dataset of 59 US cities covering the period 1970–1992 and an extended version of the panel with data through 2008.
Results
Results indicate that election cycles and firefighter hiring are “weak instruments”—weak predictors of police growth that, if used as instruments in an IV estimation, are prone to result in an unreliable estimate of the impact of police levels on crime.
Conclusions
Levitt’s preferred instruments for police levels—mayoral and gubernatorial election cycles and firefighter hiring—are weak instruments by current econometric standards and thus cannot be used to address the potential endogeneity of police in crime equations.
Original languageEnglish
Pages (from-to)133-158
Number of pages26
JournalJournal of Quantitative Criminology
Volume32
Issue number1
Early online date2 Jun 2015
DOIs
StatePublished - Mar 2016

Fingerprint

police
Police
Crime
instruments
offense
hiring
Firefighters
fire department
election
panel
test
problem
Reproducibility of Results
Datasets
crime rate
deterrence
econometrics
statement
reliability
estimation

Keywords

  • Crime
  • Endogeneity
  • Instrumental variables
  • Police

Cite this

Kovandzic, Tomislav V.; Schaffer, Mark E.; Vieraitis, Lynne M.; Orrick, Erin A.; Piquero, Alex R. / Police, Crime and the Problem of Weak Instruments : Revisiting the “More Police, Less Crime” Thesis.

In: Journal of Quantitative Criminology, Vol. 32, No. 1, 03.2016, p. 133-158.

Research output: Contribution to journalArticle

@article{bde87fd0bbc2463e88553ae8de31f375,
title = "Police, Crime and the Problem of Weak Instruments: Revisiting the “More Police, Less Crime” Thesis",
abstract = "ObjectivesA key question in the general deterrence literature has been the extent to which the police reduce crime. Definitive answers to this statement, however, are difficult to come by because while more police may reduce crime, higher crime rates may also increase police levels, by triggering the hiring of more police. One way to help overcome this problem is through the use of instrumental variables (IV). Levitt, for example, has employed instrumental variables regression procedures, using mayoral and gubernatorial election cycles and firefighter hiring as instruments for police strength, to address the potential endogeneity of police levels in structural equations of crime due to simultaneity bias.MethodsWe assess the validity and reliability of the instruments used by Levitt for police hiring using recently-developed specification tests for instruments. We apply these tests to both Levitt’s original panel dataset of 59 US cities covering the period 1970–1992 and an extended version of the panel with data through 2008.ResultsResults indicate that election cycles and firefighter hiring are “weak instruments”—weak predictors of police growth that, if used as instruments in an IV estimation, are prone to result in an unreliable estimate of the impact of police levels on crime.ConclusionsLevitt’s preferred instruments for police levels—mayoral and gubernatorial election cycles and firefighter hiring—are weak instruments by current econometric standards and thus cannot be used to address the potential endogeneity of police in crime equations.",
keywords = "Crime, Endogeneity, Instrumental variables, Police",
author = "Kovandzic, {Tomislav V.} and Schaffer, {Mark E.} and Vieraitis, {Lynne M.} and Orrick, {Erin A.} and Piquero, {Alex R.}",
year = "2016",
month = "3",
doi = "10.1007/s10940-015-9257-6",
volume = "32",
pages = "133--158",
journal = "Journal of Quantitative Criminology",
issn = "0748-4518",
publisher = "Springer New York",
number = "1",

}

Police, Crime and the Problem of Weak Instruments : Revisiting the “More Police, Less Crime” Thesis. / Kovandzic, Tomislav V.; Schaffer, Mark E.; Vieraitis, Lynne M.; Orrick, Erin A.; Piquero, Alex R.

In: Journal of Quantitative Criminology, Vol. 32, No. 1, 03.2016, p. 133-158.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Police, Crime and the Problem of Weak Instruments

T2 - Journal of Quantitative Criminology

AU - Kovandzic,Tomislav V.

AU - Schaffer,Mark E.

AU - Vieraitis,Lynne M.

AU - Orrick,Erin A.

AU - Piquero,Alex R.

PY - 2016/3

Y1 - 2016/3

N2 - ObjectivesA key question in the general deterrence literature has been the extent to which the police reduce crime. Definitive answers to this statement, however, are difficult to come by because while more police may reduce crime, higher crime rates may also increase police levels, by triggering the hiring of more police. One way to help overcome this problem is through the use of instrumental variables (IV). Levitt, for example, has employed instrumental variables regression procedures, using mayoral and gubernatorial election cycles and firefighter hiring as instruments for police strength, to address the potential endogeneity of police levels in structural equations of crime due to simultaneity bias.MethodsWe assess the validity and reliability of the instruments used by Levitt for police hiring using recently-developed specification tests for instruments. We apply these tests to both Levitt’s original panel dataset of 59 US cities covering the period 1970–1992 and an extended version of the panel with data through 2008.ResultsResults indicate that election cycles and firefighter hiring are “weak instruments”—weak predictors of police growth that, if used as instruments in an IV estimation, are prone to result in an unreliable estimate of the impact of police levels on crime.ConclusionsLevitt’s preferred instruments for police levels—mayoral and gubernatorial election cycles and firefighter hiring—are weak instruments by current econometric standards and thus cannot be used to address the potential endogeneity of police in crime equations.

AB - ObjectivesA key question in the general deterrence literature has been the extent to which the police reduce crime. Definitive answers to this statement, however, are difficult to come by because while more police may reduce crime, higher crime rates may also increase police levels, by triggering the hiring of more police. One way to help overcome this problem is through the use of instrumental variables (IV). Levitt, for example, has employed instrumental variables regression procedures, using mayoral and gubernatorial election cycles and firefighter hiring as instruments for police strength, to address the potential endogeneity of police levels in structural equations of crime due to simultaneity bias.MethodsWe assess the validity and reliability of the instruments used by Levitt for police hiring using recently-developed specification tests for instruments. We apply these tests to both Levitt’s original panel dataset of 59 US cities covering the period 1970–1992 and an extended version of the panel with data through 2008.ResultsResults indicate that election cycles and firefighter hiring are “weak instruments”—weak predictors of police growth that, if used as instruments in an IV estimation, are prone to result in an unreliable estimate of the impact of police levels on crime.ConclusionsLevitt’s preferred instruments for police levels—mayoral and gubernatorial election cycles and firefighter hiring—are weak instruments by current econometric standards and thus cannot be used to address the potential endogeneity of police in crime equations.

KW - Crime

KW - Endogeneity

KW - Instrumental variables

KW - Police

UR - http://www.scopus.com/inward/record.url?scp=84930352976&partnerID=8YFLogxK

U2 - 10.1007/s10940-015-9257-6

DO - 10.1007/s10940-015-9257-6

M3 - Article

VL - 32

SP - 133

EP - 158

JO - Journal of Quantitative Criminology

JF - Journal of Quantitative Criminology

SN - 0748-4518

IS - 1

ER -