JSM 2015 Online Program

Online Program Home
My Program

Abstract Details

Activity Number: 78
Type: Contributed
Date/Time: Sunday, August 9, 2015 : 4:00 PM to 5:50 PM
Sponsor: Survey Research Methods Section
Abstract #314868 View Presentation
Title: Small-Area Estimates of Crime Rates for States and Large Counties Based on the NCVS
Author(s): Bob Fay* and Mamadou S. Diallo
Companies: Westat and Westat
Keywords: EBLUP ; Rao-Yu model ; Fay-Herriot model

The National Crime Victimization Survey (NCVS) in the U.S. has provided estimates of violent and property crime for over four decades. Until recently, the survey has had almost exclusively a national focus. As recommended by a National Academy of Sciences panel, the Bureau of Justice Statistics (BJS) has undertaken a number of efforts to expand the geographic utility of the survey results. This paper is an outgrowth of research to provide small area estimates of key crime rates from the NCVS for states, large counties, and large metropolitan areas. The estimates are based a modified version of a time-series model proposed by Rao and Yu to take advantage of strong area-level correlations in the estimates over time. A multivariate version of the model was used to provide estimates for components of the crime rates by type of crime and by relationship to the perpetrator. BJS plans to make the estimates available to users on their website. This paper describes a hybrid model representing a further extension. These methods have potential applications to other situations in which the underlying characteristic exhibits strong stability over time.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2015 program

For program information, contact the JSM Registration Department or phone (888) 231-3473.

For Professional Development information, contact the Education Department.

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

2015 JSM Online Program Home