|
These data provide information on criminal homicides including location, circumstances, and method of offense, as well as demographic characteristics of victims and perpetrators and the relationship between the two. The data were provided monthly to the Federal Bureau of Investigation (FBI) by local law enforcement agencies participating in the FBI's Uniform Crime Reporting Program. As part of an on-going project the data from the FBI have been restructured and compiled into cumulative files covering the years 1976-1998. James A. Fox, Northeastern University, provided the restructured and compiled data (ICPSR 3000) used here.
Study Design
Law enforcement agencies that reported criminal homicides on the basic UCR Return A form (from which come the Offenses Known and Clearances by Arrest data files) were requested but not required to submit a Supplementary Homicide Report (SHR) for each month in which homicides became known. The SHR was not submitted by agencies for months in which no homicides were reported to police.
UCR Program contributors compile and submit their crime data by one of two means: either directly to the FBI or through their State UCR Programs. State UCR programs frequently impose mandatory reporting requirements which have been effective in increasing both the number of reporting agencies as well as the number and accuracy of each participating agency's reports.
The Supplementary Homicide Reports provide incident-level details on location, victim, and offender characteristics. Specifically, these data include information on the month and year of an offense, on the reporting agency and its residential population, county and Metropolitan Statistical Areas (MSA) codes, geographic division and population group, on the age, race, and sex of victims and offenders, and on the victim/offender relationship, weapon use, and circumstance of the crime. For the years 1976-1998, contributing agencies provided homicide reports for 439,954 of the estimated 481,500 murder victims, and for 486,359 of the estimated 532,463 offenders.
Although national coverage is quite high (about 92% of homicides are included in the SHR), missing reports can be corrected using weights to match national and state estimates prepared by the FBI. The most significant problem in using SHR data to analyze offender characteristics, however, is the sizable and growing number of unsolved homicides contained in the data file. To the extent that the missing offender data is associated with certain offender characteristics, ignoring unsolved homicides would seriously underestimate rates of offending by particular sub-groups of the population, distort trends over time among these same sub-groups, and bias observed patterns of offending. To adjust for unsolved homicides, a method for offender imputation has been devised, using available information about the victims murdered in both solved and unsolved homicides. Through this imputation algorithm, the demographic characteristics of unidentified offenders are inferred on the basis of similar homicide cases--similar in terms of the victim profile and state and year of the offense--that had been solved. In other words, offender profiles for unsolved crimes are estimated based on the offender profiles in solved cases matched on victim age, sex, and race as well as year and state.
The weights WTIMPUS and WTIMPST only use cases for which offender age, race and sex are available, and impute all others. WTIMPUS2 and WTIMPST2 use cases for which offenders are known, even if age, race or sex is missing, and impute all others.
Finally, users of the imputation weights are cautioned in relying on weights for subsamples (e.g., one jurisdiction) where a significant portion of cases have missing offender data and thus imputation weights are relatively large.
Unit of Analysis
The source data, the FBI's Supplemental Homicide Reports, are organized with the homicide incident as the unit of analysis. However, this collection contains two files with two different units of analysis. Part 1 has the victim as the unit of analysis, while Part 2 has the offender as the unit of analysis.
Multiple Offenders
ICPSR dataset number 3000 is comprised of two data files, one for victims and one for offenders. For homicide incidents involving more than one victim or offender each victim is listed in the victim file, and each offender is listed in the offender file.
Both the victim file and the offender file contain some information from the other file. That is, the victim file contains mostly information about the homicide victim; however, it also contains some information from the offender file. In the situation of multiple offenders, only the information from the first offender is listed on the victim file. The corresponding situation exists with the offender file and multiple victims.
Data Collection Notes
Further details regarding the Uniform Crime Reporting Program may be found in the following related publications:
Federal Bureau of Investigation. Crime in the United States: Uniform Crime Reports for the United States. Washington, D.C.: U.S. Government Printing Office, 1999.
Federal Bureau of Investigation. Uniform Crime Reporting Handbook. Washington, D.C.: U.S. Government Printing Office, 1984.
|
