Online Program Home
My Program

Abstract Details

Activity Number: 252 - SPEED:Improving Survey Data Quality with Multiple Data Sources, Administrative Data, and Nonresponse Bias Control, Part 2
Type: Contributed
Date/Time: Monday, July 29, 2019 : 2:00 PM to 2:45 PM
Sponsor: Survey Research Methods Section
Abstract #307630
Title: Coverage Error in Administrative Data: An Assessment of the National Incident Based Reporting System
Author(s): Sarah Zimmermann* and Dan Liao and Marcus Berzofsky and Alexia Cooper
Companies: RTI International and RTI International and RTI and Bureau of Justice Statistics
Keywords: Coverage Assessment; Administrative Data; Crime Statistics; Data Quality Assessment; Coverage Ratio; Sample Representativeness

Using administrative data to create official statistics is an increasingly common practice; these records do not incur collection costs or impose burden on respondents. Administrative data, however, often come from multiple sources. If not all sources report data, then the administrative data will suffer from coverage error which, if severe enough, can lead to bias in the official statistics. The FBI’s National Incident-Based Reporting System (NIBRS) is one type of administrative data which collects information on reported crime and arrests. NIBRS has the potential to create official crime statistics but illustrates issues in coverage as only about a third of the law enforcement agencies in the U.S. report using this system. Moreover, the agencies which report data do not include the largest metropolitan areas. This presentation discusses ways to assess and quantify the coverage error of NIBRS. In order to quantify, we use auxiliary information to measure coverage and its impacts on bias. The proposed method can be applied to other administrative data ultimately informing the final weighting strategies used to produce official statistics.

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

Back to the full JSM 2019 program