Optimizing the Use of Video Technology to Improve Criminal Justice Outcomes, Milwaukee, WI, 2017-2018 (ICPSR 37683)
Version Date: Feb 28, 2022 View help for published
Principal Investigator(s): View help for Principal Investigator(s)
Daniel S. Lawrence, Urban Institute;
Bryce E. Peterson, Urban Institute
https://doi.org/10.3886/ICPSR37683.v1
Version V1
Summary View help for Summary
The goal of this project was to analyze the collaboration between the Urban Institute and Milwaukee Police Department (MPD) to develop a plan to optimize MPD's public surveillance system. This was done through a process and impact evaluation of the MPD's strategy to improve operations, install new cameras, and integrate video analytic (VA) technologies centered around automatic license plate recognition (ALPR) and high-definition cameras connected to gunshot detection technology. The unit of analysis was two neighborhoods in Milwaukee, identified as "focus areas" by the researchers, where VA efforts were intensified. Additionally, all block groups within Milwaukee were included to measure crime before and after intervention, along with all intersections and block groups that received VA technologies against control groups. Variables include crimes based on date and location, along with whether or not locations had VA technologies. The following neighborhood demographic variables were included from the United States Census Bureau: resided in a different home, renters, under age eighteen, black residents, female headed households, public assistance recipients, below poverty line, unemployment, Hispanic residents, and foreign born.
Citation View help for Citation
Export Citation:
Funding View help for Funding
Subject Terms View help for Subject Terms
Geographic Coverage View help for Geographic Coverage
Smallest Geographic Unit View help for Smallest Geographic Unit
Census Block Group
Restrictions View help for Restrictions
Access to these data is restricted. Users interested in obtaining these data must complete a Restricted Use Agreement, specify the reasons for the request, and obtain IRB approval or notice of exemption for their research.
Distributor(s) View help for Distributor(s)
Time Period(s) View help for Time Period(s)
Date of Collection View help for Date of Collection
Study Purpose View help for Study Purpose
In 2016, the National Institute of Justice funded the Urban Institute's "Optimizing the Use of Video Technology to Improve Criminal Justice Outcomes" project, with the goal of collaborating with the Milwaukee Police Department (MPD) to improve the agency's public surveillance network. The central objective of this study was to perform a process and impact evaluation of the steps the MPD took to optimize its network, including improving operations, installing new cameras, and integrating video analytic (VA) technologies into its system.
The VA technologies integrated include automatic license plate recognition (ALPR) cameras and Pan-Tilt-Zoom (PTZ) cameras linked to the city's gunshot technologies. In January 2018, the MPD expanded its cameras from 42 to 87, with 24 new panoramic cameras, 12 PTZ cameras, 9 ALPR cameras, and relocating two old PTZ to more appropriate locations. Once these changes were implemented, the Urban Institute conducted a process and outcome evaluation of VA use. For the process assessment, they reviewed administrative and program materials, and conduct stakeholder interviews. Then the outcome assessment looked at administrative and incident-level crime data pre and post VA technology, then reviewed VA data to match with departmental case files. Furthermore, the Urban Institute conducted a cost-benefit analysis to assess whether or not the benefits in VA outcomes outweigh the costs of the technology.
Study Design View help for Study Design
The research team utilized qualitative and quantitative sources to review the Milwaukee Police Department's (MPD) camera program. Qualitative data collection included observations of the department's camera operations to identify best practices and determine areas of improvement. Additionally, interviews were conducted with camera operators, camera program supervisors, shift commanders, crash reconstruction unit officers, specialized investigations division officers, criminal investigations bureau detectives, and civilian managers from the department's communication division.
Numerous quantitative data sources were collected, including administrative crime data, metadata from the camera system, and costs related to system upgrades. The impact of interventions on crime levels was assessed using a negative binomial panel regression analysis with different samples to measure percentage differences in crime pre- and post-implementation, on average. Crime outcomes included violent crime, property crime, simple assaults, minor offenses (Group B), offenses that involved a firearm, vandalism, drug crimes, and weapon law violations. Quarterly time periods were used to track changes, while controlling for land use, and concentrated disadvantage.
Comparison areas were identified using propensity score matching to conduct difference-in-differences analyses. The sample included the entire city of Milwaukee, all intersections with a new camera, intersections that previously did not have a camera but had a new camera installed, intersections that previously did have a camera but also had a new camera installed, intersections where Pan-Tilt-Zoom (PTZ) cameras were connected to gunshot detection technology (GDT), areas with automatic license plate recognition (ALPR) cameras, and two "focus areas" neighborhoods: Center Street Corridor (CSC) and Muskego Way.
These focus areas were identified by the researchers using analyses of violent and property crime, GDT alerts, stolen and recovered vehicle data, and knowledge from MPD staff, in order to focus camera optimization efforts in strategic areas. CSC increased its cameras from seven cameras at five intersections, to twenty-five cameras at fifteen intersections. Muskego Way went from eight cameras at eight locations, to twenty-three cameras at fifteen intersections.
Time Method View help for Time Method
Universe View help for Universe
Neighborhoods, block groups, and street intersections in Milwaukee, Wisconsin from 2017 to 2018.
Unit(s) of Observation View help for Unit(s) of Observation
Data Source View help for Data Source
United States Census Bureau. American Community Survey.
Data Type(s) View help for Data Type(s)
Mode of Data Collection View help for Mode of Data Collection
Response Rates View help for Response Rates
Not applicable.
Presence of Common Scales View help for Presence of Common Scales
none
HideNotes
The public-use data files in this collection are available for access by the general public. Access does not require affiliation with an ICPSR member institution.
One or more files in this data collection have special restrictions. Restricted data files are not available for direct download from the website; click on the Restricted Data button to learn more.