Activity Number:
|
298
- SPEED: Innovations in Survey Sampling Designs: Administrative Data, Record Linkage, Non-Probability Samples, and More
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, July 31, 2018 : 8:30 AM to 10:20 AM
|
Sponsor:
|
Government Statistics Section
|
Abstract #329401
|
|
Title:
|
Different Linkage Methods, Same Results? Linking National Center for Health Statistics Survey Data to Centers for Medicare and Medicaid Administrative Records
|
Author(s):
|
Cordell Golden* and Adam Fedorowicz and Lisa B Mirel
|
Companies:
|
National Center for Health Statistics (NCHS) and National Center for Health Statistics (NCHS) and National Center for Health Statistics (NCHS)
|
Keywords:
|
NCHS Data Linkage Program;
Health Survey Data;
Dual Eligibles;
Deterministic;
Probabilistic
|
Abstract:
|
Through its data linkage program, the National Center for Health Statistics (NCHS) routinely links its health survey data with vital and administrative records, including the National Death Index, the U.S. Department of Housing and Urban Development and the Centers for Medicare & Medicaid Services (CMS). The datasets created as a result of these linkages provide a rich source of information for a variety health-related topics and methodological research. The recent linkages of NCHS survey data with CMS administrative records offer a unique opportunity to compare results from two different linkage methodologies for survey participants deemed dual-eligible or eligible for Medicare and Medicaid benefits. The first linkage was conducted with NCHS survey data and CMS Medicare data using a deterministic (rules based) approach. The same survey participants were then linked with Medicaid administrative records using a probabilistic approach based on the Felligi-Sunter methodology. This talk with describe the methods used for the independent linkages and a comparison of the results for survey participants who were enrolled in both Medicare and Medicaid and linked to both sources.
|
Authors who are presenting talks have a * after their name.