Online Program Home
My Program

Abstract Details

Activity Number: 25
Type: Topic Contributed
Date/Time: Sunday, July 31, 2016 : 2:00 PM to 3:50 PM
Sponsor: Business and Economic Statistics Section
Abstract #321049
Title: Comparing Survey and Administrative Earnings: An Application of Employer-List Linking
Author(s): Lori Reeder* and Holly Monti
Companies: and U.S. Census Bureau
Keywords:
Abstract:

We employ a data-linking practice wherein we use a record-linking software to link SIPP-reported employer names to the business names linked to the respondent's W-2 records as reported in the Detailed Earnings Record (DER), extracted from the Social Security Administration Master Earnings File. By linking a respondent's SIPP job to the correct W-2 earnings record, we are able to compare a respondent's reported earnings at the specific job to their actual W-2 reports for that same job. Prior to linking a SIPP respondent's job to a W-2, we would be constrained to comparing total earnings from all jobs reported on the SIPP to the sum of all W-2 earnings in a given year. Once we have linked SIPP-reported jobs to the correct W-2, we can compare SIPP-reported job-level earnings to administrative record earnings. We examine both measures of earnings for potential differences across several dimensions, including demographic characteristics. Furthermore, we consider characteristics of a respondent's current employment, in particular, industry and firm size. The latter two characteristics are linked to respondents' W-2 records in the same manner as business name.


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

Back to the full JSM 2016 program

 
 
Copyright © American Statistical Association