National Archive of Criminal Justice Data

This dataset is maintained and distributed by the National Archive of Criminal Justice Data (NACJD), the criminal justice archive within ICPSR. NACJD is primarily sponsored by three agencies within the U.S. Department of Justice: the Bureau of Justice Statistics, the National Institute of Justice, and the Office of Juvenile Justice and Delinquency Prevention.

Evaluation of the Shreveport, Louisiana Predictive Policing Programs, 2011-2012 (ICPSR 36031)

Principal Investigator(s): Hollywood, John, RAND Corporation

Summary:

These data are part of NACJD's Fast Track Release and are distributed as they were received from the data depositor. The files have been zipped by NACJD for release, but not checked or processed except for the removal of direct identifiers. Users should refer to the accompanying readme file for a brief description of the files available with this collection and consult the investigator(s) if further information is needed.

This collection was part of a larger two-phase project funded by the National Institute of Justice (NIJ). Phase I focused on the development and estimation of predictive crime models in Shreveport, Louisiana and Chicago, Illinois. Phase II involved the implementation of a prevention model using the predictive model. To evaluate the two predictive policing pilot programs funded by NIJ, RAND evaluated the predictive and preventative models employed by the Shreveport Police Department titled Predictive Intelligence Led Operational Targeting (PILOT). RAND evaluated whether PILOT was associated with a measurable reduction in crime. The data were used to determine whether or not there was a statistically significant reduction in property crime counts in treated districts versus control districts in Shreveport.

The collection includes 1 Excel file (Shreveport_Predictve_Policing_Evaluation_Experiment_Data.xlsx (n=91; 8 variables)) related only to the property crime aspect of the study. Neither data used to perform the outcomes evaluation for the Chicago Police Department experiment nor qualitative data used to help perform the prediction and prevention model evaluations are available.

Access Notes

  • These data are part of NACJD's Fast Track Release and are distributed as they were received from the data depositor. The files have been zipped by NACJD for release, but not checked or processed except for the removal of direct identifiers. Users should refer to the accompanying readme file for a brief description of the files available with this collection and consult the investigator(s) if further information is needed.

  • One or more files in this data collection have special restrictions ; consult the restrictions note to learn more. You can apply online for access to the restricted-use data. A login is required to apply.

    Access to these data is restricted. Users interested in obtaining these data must complete a Restricted Data Use Agreement, specify the reasons for the request, and obtain IRB approval or notice of exemption for their research.

    Any 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.

Dataset(s)

Dataset
Documentation:
Download:
No downloadable data files available.

Study Description

Citation

Hollywood, John. Evaluation of the Shreveport, Louisiana Predictive Policing Programs, 2011-2012. ICPSR36031-v1. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2017-12-06. https://doi.org/10.3886/ICPSR36031.v1

Persistent URL: https://doi.org/10.3886/ICPSR36031.v1

Export Citation:

  • RIS (generic format for RefWorks, EndNote, etc.)
  • EndNote XML (EndNote X4.0.1 or higher)

Funding

This study was funded by:

  • United States Department of Justice. Office of Justice Programs. National Institute of Justice (2009-IJ-CX-K114)

Scope of Study

Subject Terms:    crime control programs, crime mapping, crime prediction, police effectiveness, police performance

Smallest Geographic Unit:    police districts

Geographic Coverage:    Louisiana, Shreveport, United States

Time Period:   

  • 2011--2012

Date of Collection:   

  • 2012

Unit of Observation:    police districts

Universe:    Monthly property crime counts by police district in Shreveport, Louisiana

Data Type(s):    administrative records data, aggregate data, event/transaction data

Data Collection Notes:

These data are part of NACJD's Fast Track Release and are distributed as they were received from the data depositor. The files have been zipped by NACJD for release, but not checked or processed except for the removal of direct identifiers. Users should refer to the accompanying readme file for a brief description of the files available with this collection and consult the investigator(s) if further information is needed.

Data used to perform the outcomes evaluation are not available for the Chicago Police Department experiment. This experiment tested whether a predictive policing effort to treat persons assessed as being at high risk of being a homicide victim resulted in fewer crime and victimization reports. As a result, the data provided by the Chicago Police Department was both law enforcement sensitive and contained a number of direct and indirect identifiers.

Qualitative data used to help perform the prediction and prevention model evaluations are unavailable. These consisted of detailed and sensitive interview notes from district commanders and executive officers.

Methodology

Study Purpose:    The purpose of this study was to evaluate the effectiveness of predictive policing strategies used by the Shreveport, Louisiana Police Department that were developed by crime estimation and predictive models.

Study Design:   

This collection is part of a larger two-phase study funded by the National Institute of Justice (NIJ). Following a year long planning phase grant from the NIJ, the Shreveport, Louisiana Police Department (SPD) developed its own statistical models for predicting crime based on leading indicators using multivariate logistic regression analysis for grid city-blocks, 400 feet by 400 feet.

Following the development of a prediction model, the SPD implemented a field experiment of Predictive Intelligence Led Operational Targeting (PILOT), using the predictive model in order to deploy overtime labor to the predicted hot spots. The specific resource allocation decisions and specific strategies to be employed by the officers in the experimental districts was determined by the SPD in monthly planning meetings.

Following the SPD's PILOT trial, RAND researchers evaluated the PILOT trial. RAND researchers conducted multiple interviews and focus groups with the SPD throughout the course of the trial to document the implementation of the predictive and prevention models. Furthermore, RAND evaluated the impact of the PILOT strategies on levels of property crime as a whole and by type of crime by testing differences between treatment and control districts and applying advanced program evaluation techniques (e.g., difference-in-difference methods). Finally, RAND evaluated the expenses of PILOT using a cost savings analysis (CSA) using administrative and supplemental secondary data. The data in this collection only focus on the property crime aspect of the study.

Sample:    Shreveport Police Department staff developed and estimated a statistical model of the likelihood of property crimes occurring within block-sized areas. Then, using a blocked randomized approach to identify three treatment and control district pairs, districts assigned to the treatment group were given maps that highlighted blocks predicted to be at higher risk of property crime. These three treatment districts were also provided with overtime resources to conduct special operations. The three Control districts conducted property crime-related special operations using overtime resources as well, just targeting areas that had recently seen property crimes (hot spots).

Time Method:    Longitudinal: Trend / Repeated Cross-section

Weight:    None

Mode of Data Collection:    record abstracts

Description of Variables:   

The dataset (n=91) consists of 8 variables.

The dataset contains time variables that are related to the experimental and control periods within the study. These variables include Month, Year, and Time.

The dataset contains variables related to the experimental and control districts within the study. These variables include District, Chief, and Treat.

The dataset contains variables that were used to measure a reduction in crime as a result of predictive policing tactics. These variables include Crime_total and Manhours.

Response Rates:    Not applicable

Presence of Common Scales:    None

Version(s)

Original ICPSR Release:   2017-12-06

Utilities

Metadata Exports

If you're looking for collection-level metadata rather than an individual metadata record, please visit our Metadata Records page.

Download Statistics