Uniform Crime Reporting (UCR) Program Data: County-Level Detailed Arrest and Offense Data
- Kaplan, Jacob (University of Pennsylvania)
Abstract!!! Important Note: There are a number of flaws in the imputation process to make these county-level files. Included as one of the files to download (and also in every zip file) is Maltz & Targonski's 2002 paper on these flaws and why they are such an issue. I very strongly recommend that you read this paper in its entirety before working on this data. I am only publishing this data because people do use county-level data anyways and I want them to know of the risks. Important Note !!!
The following paragraph is the abstract to Maltz & Targonski's paper:
County-level crime data have major gaps, and the imputation schemes for filling in the gaps are inadequate and inconsistent. Such data were used in a recent study of guns and crime without considering the errors resulting from imputation. This note describes the errors and how they may have affected this study. Until improved methods of imputing county-level crime data are developed, tested, and implemented, they should not be used, especially in policy studies.
The agency-level data used to make these files are the Offenses Known and Clearances by Arrest 1960-2017 (https://www.openicpsr.org/openicpsr/project/100707/version/V9/view) and Arrests by Age, Sex, and Race 1974-2016 (https://www.openicpsr.org/openicpsr/project/102263/version/V7/view) data that I have released. For the code I used to create these files please see here: https://github.com/jacobkap/crime_data/blob/master/R/county_data.R.
This data aggregates agency-level crime and arrest data into county-level counts. Which county each agency is in is based on the FIPS state-county code in the LEAIC (crosswalk) file which is already joined with the agency-level data. I also add a column with the county name based on the census data set Annual Survey of Public Employment & Payroll (ASPEP) (https://www.openicpsr.org/openicpsr/project/101399/version/V5/view). For agencies that do not report, or report fewer than all 12 months of the years, I use the following imputation procedure designed by NACJD. The imputation process is the same as NACJD's process except while they exclude offenses with zero months reported I do include them.
- Agencies reporting between 3 and 11 months have their crimes/arrests multiplied by 12/number of months reported. Such that an agency that reports only 6 months out of the year and says there were 10 murders would be estimated to have had 20 murders in the years (10 murders * 12/6 months reported = 10 * 2 = 20).
- Agencies reporting fewer than 3 months would simply have the average (mean) number of arrests for agencies in that state, year, and population group (e.g. cities population 250,000+, cities population 10,000-24,999). This average is generated only by agencies that reported all 12 months of the year! Such that if an agency reported 15 murders and only reported 2 months of the year, that agency would get the average number of murders for similar sized agencies (same population group) in that state during that year.
- Agencies with a population of 0 (common in special agencies such as state police, universities, park police) and fewer than 3 months reported are dropped as they have no population group to match to.
1960-01-01 / 2017-12-31Time Period: Fri Jan 01 00:00:00 EST 1960--Sun Dec 31 00:00:00 EST 2017 (1960-2017 for crime data, 1974-2016 for arrest data)
Counties in the United States
Update Metadata: 2019-01-22 | Issue Number: 1 | Registration Date: 2019-01-22