Multiple Imputation for the Supplementary Homicide Reports: Evaluation in Unique Test Data, 1990-1995, Chicago, Philadelphia, Phoenix and St. Louis (ICPSR 36379)

Principal Investigator(s): Roberts, John, University of Wisconsin-Milwaukee; Roberts, Aki, University of Wisconsin-Milwaukee

Summary:

This study was an evaluation of multiple imputation strategies to address missing data using the New Approach to Evaluating Supplementary Homicide Report (SHR) Data Imputation, 1990-1995 (ICPSR 20060) dataset.

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.

  • 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.

Dataset(s)

Dataset - Download All Files (638.832 MB) large file
Documentation:
Download:

Study Description

Citation

Roberts, John, and Aki Roberts. Multiple Imputation for the Supplementary Homicide Reports: Evaluation in Unique Test Data, 1990-1995, Chicago, Philadelphia, Phoenix and St. Louis. ICPSR36379-v1. Ann Arbor, MI: Inter-university Consortium for Political and Social Research [distributor], 2016-03-31. https://doi.org/10.3886/ICPSR36379.v1

Persistent URL: https://doi.org/10.3886/ICPSR36379.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 (2013-R2-CX-0038)

Scope of Study

Subject Terms:    crime reporting, crime statistics, murder, offenders, Uniform Crime Reports, victims

Smallest Geographic Unit:    City

Geographic Coverage:    Arizona, Chicago, Illinois, Missouri, Pennsylvania, Philadelphia, Phoenix, St. Louis, United States

Time Period:   

  • 1990--1995

Date of Collection:   

  • 1990--1995

Unit of Observation:    Homocide

Universe:    Homicides known to the police in Chicago, Illinois, Philadelphia, Pennsylvania, Phoenix, Arizona, St. Louis, Missouri, from 1990 to 1995.

Data Type(s):    administrative records 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.

These data were constructed from the Evaluating Supplementary Homicide Report (SHR) Data Imputation, 1990-1995 (ICPSR 20060) dataset. For instructions on how to replicate these data please see the appendix of the codebook.

Methodology

Study Purpose:   

The purpose of the study was to evaluate the effectiveness of multiple imputation strategies in addressing missing data in the Supplementary Homicide Report (SHR) data. The specific goals of the study were as follows:

  1. In the test population, evaluated multiple imputation methods by comparing imputed and actual distributions of victim-offender relationship.
  2. In the test population, evaluated multiple imputation methods by comparing results obtained for imputed and actual data in analysis of substantive models of criminological interest.
  3. Extended the work pursuant to the first and second goals to include the impact on these comparisons of choices such as particular methods for multiple imputation and the number of imputations used, and evaluate the Uniform Crime Reports [United States]: Supplementary Homicide Reports With Multiple Imputation, Cumulative Files 1976-2007 (ICPSR 24801) data in this context.

Study Design:   

New Approach to Evaluating Supplementary Homicide Report (SHR) Data Imputation, 1990-1995 (ICPSR 20060) dataset was selected as it included incidents in which offender information was recorded as missing in the SHR data, but was recovered from police records. This test population enabled the evaluation of multiple imputation strategies and comparisons of imputed and actual data in various ways.

Sample:    Not applicable.

Time Method:    Cross-sectional

Mode of Data Collection:    record abstracts

Data Source:

New Approach to Evaluating Supplementary Homicide Report (SHR) Data Imputation, 1990-1995 (ICPSR 20060).

Description of Variables:   

Main Data Version 1 (n=6,573) includes 18 variables on the details of the incident, demographics of the victim, demographics of the offender, victim and offender relationship, and source of victim and offender relationship information.

Main Data Version 2 (n=6,573) includes 15 variables on the details of the incident, demographics of the victim, and demographics of the offender. This dataset includes the same incidents as Main Data Version 1 with some of the missing data filled in with information from police reports.

Imputation Version 1 to 4 datasets each contain 1,000 imputations generated using IVEWare software. They differ in the number of variables used to create the imputations. Only variables used for the imputations are included in each file.

  • Imputation Version 1 data (n=6,573,000) includes 5 variables on year, victim/offender relationship, imputation number, jurisdiction, and ID.
  • Imputation Version 2 data (n=6,573,000) includes 9 variables on year, calendar season, victim/offender relationship, victim demographics, imputation number, jurisdiction, and ID.
  • Imputation Version 3 data (n=6,573,000) includes 11 variables on year, calendar season, circumstance of incident, victim/offender relationship, victim demographics, imputation number, jurisdiction, and ID.
  • Imputation Version 4 data (n=6,573,000) includes 14 variables on year, calendar season, circumstance of incident, victim/offender relationship, victim demographics, offender demographics, imputation number, jurisdiction, and ID.

SAS MCMC and SAS MCMC No Bounds datasets each contain 1,000 imputations generated using the normal-MCMC routine in SAS. Each dataset (n=6,573,000) includes 31 variables on year, calendar season, circumstance of incident, victim/offender relationship, victim demographics, offender demographics, imputation number, jurisdiction, and ID. The no bounds version of the SAS MCMC dataset does not impose bounds on the numerical value of the victim and offender age variables.

Version(s)

Original ICPSR Release:   2016-03-31

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