Assessing the Association Between the Crime Rates from the National Crime Victimization Survey and the Uniform Crime Reporting Program

• Activity Number: 686
• Type: Contributed
• Date/Time: Thursday, August 5, 2010 : 10:30 AM to 12:20 PM
• Sponsor: Section on Survey Research Methods
• Author(s): Jianzhu Li*+ and Robert E. Fay
• Companies: Westat and Westat
• Keywords: property crime ; violent crime ; simple assault

Abstract

The National Crime Victimization Survey (NCVS) is a major crime survey for the United States and has been facing the problem of increasing costs of data collection and a diminishing budget. The Uniform Crime Reporting (UCR) Program is another national indicator of crime, which collects crime data from the reporting of law enforcement jurisdictions. Our study used linear regressions to assess the statistical relationship between the NCVS and UCR crime rates at the county level. We found that UCR can strongly predict the NCVS crime rates, especially when the UCR data are most completely reported. The relationship between crime rates provides a potential to improve the NCVS sample design features, e.g., stratification of non-self-representing PSUs or oversampling areas with high crime rates, so that higher efficiency and more precision can be achieved within the budget constraint.