Abstract
Using domestic violence incidence and arrest data from Maryland (1991–1997), this research examines whether the proportion of incidents that result in arrest increased due to a legislative initiative implemented in 1994 and, if so, whether this change is uniform across different types of offenders (race and gender) and offense characteristics. Using interrupted time‐series analysis (ARIMA), we observe an increase in both the number of incidents reported to police and the percent of reported cases resulting in arrest. The legislative intervention has a significant positive impact on arrest likelihood above and beyond the increase over time for the state as a whole. While arrest probabilities increased across the board for males and females, African American and Whites, the ARIMA models do not suggest that the legislation differentially impacted arrest probabilities for these groups.
Acknowledgments
This research was supported by a grant from the state of Maryland Governor’s Office of Crime Control and Prevention with support from the Grants to Encourage Arrest Program of the Violence Against Women Grant Office of the US Department of Justice. Points of view are those of the authors and do not necessarily reflect those of the Governor’s Office, the US Department of Justice, or the University of Maryland.
Notes
1. The formula for the coefficient difference z‐test is: . See Paternoster, Brame, Mazerolle, and Piquero (Citation1998), for a discussion of coefficient difference tests.
2. There is no global test for differences between more than two coefficients (Paternoster, 2005, personal communication). In this analysis, we use the standard coefficient comparison z‐test (Paternoster et al., Citation1998). With multiple comparisons, this does raise a concern about alpha inflation. To account for this possibility, we have used a higher level of significance (.01).
Paternoster
,
R.
,
Brame
,
R.
,
Mazerolle
,
P.
and
Piquero
,
A.
1998
.
Using the correct statistical test for the quality of regression coefficients
.
Criminology
,
26
:
859
–
866
.
Paternoster
,
R.
,
Brame
,
R.
,
Mazerolle
,
P.
and
Piquero
,
A.
1998
.
Using the correct statistical test for the quality of regression coefficients
.
Criminology
,
26
:
859
–
866
.
Additional information
Notes on contributors
Sally S. Simpson
Sally S. Simpson is Professor and Chair of Criminology and Criminal Justice at the University of Maryland, College Park. Her research interests include corporate crime, criminological theory, and the intersection between gender, race, class, and crime. She is author of Corporate Crime, Law and Social Control (2002, Cambridge University Press) and Of Crime & Criminality (2000, Pine Forge Press). Her recent articles have appeared in Criminology, Justice Quarterly, and Law & Society Review.
Leana Allen Bouffard
Dr Bouffard is an Assistant Professor of Criminal Justice at Washington State University. Her Research Interests include violence against women, quantitative methods, and criminology theory.
Joel Garner
Joel H. Garner is the Director of Research at the Joint Centers for Justice Studies, Inc. His research interests include the effectiveness of criminal justice responses to intimate partner violence, police use of force, federal firearm regulation, racial profiling, and alternative forms of research synthesis.
Laura Hickman
Laura J. Hickman is a Behavioral Scientist at the RAND Corporation, Associate Professor of Criminal Justice at the Pardee RAND Graduate School, and Adjunct Professor of Sociology at University of Massachusetts Amherst. Her work focuses on evaluating programs and policy responses to crime and victimization, including an evaluation of a 15‐site federal initiative to implement programs intended to ameliorate the negative impacts of children’s exposure to violence.