Online Program Home
  My Program

Abstract Details

Activity Number: 181 - Contributed Poster Presentations: Government Statistics Section
Type: Contributed
Date/Time: Monday, July 31, 2017 : 10:30 AM to 12:20 PM
Sponsor: Government Statistics Section
Abstract #323691
Title: Combining Survey and Non-Survey Data Sources to Improve Estimated Counts of Certain Work-Related Injuries
Author(s): Brooks Pierce*
Companies: U.S. Bureau of Labor Statistics
Keywords: data combination ; administrative data ; work-related injuries
Abstract:

The Survey of Occupational Injuries and Illnesses (SOII) is the primary survey of nonfatal work-related injuries and illnesses in the U.S. Recently the Occupational Safety and Health Administration (OSHA) has instituted new rules governing employer report of work-related injuries, raising the possibility that OSHA administrative data could be combined with SOII survey data to improve estimates of injury risks in the workplace. This paper utilizes newly available OSHA administrative records on severe injury cases to investigate the potential for such data combination. I give a qualitative assessment of operational issues arising from using OSHA administrative records to inform SOII estimates. I also provide evidence from linked OSHA and SOII data indicating non-random reporting to the OSHA source, which would need to be accounted for in any data combination attempt.


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

Back to the full JSM 2017 program

 
 
Copyright © American Statistical Association