Using Extant Lists to Improve CAPI Instruments and Expedite Record Linkage

• Activity Number: 676
• Type: Topic Contributed
• Date/Time: Thursday, August 13, 2015 : 10:30 AM to 12:20 PM
• Sponsor: Survey Research Methods Section
• Author(s): Felicia LeClere* and Jennifer Vanicek and Joe Matise and Sandra Tilmon and John Christopher McCormick
• Companies: NORC at the University of Chicago and NORC at the University of Chicago and NORC at the University of Chicago and NORC at the University of Chicago and Centers for Medicare and Medicaid Services
• Keywords: Survey methodology ; CAPI methods ; MCBS

Abstract

The Medicare Current Beneficiary Survey is an overlapping panel survey conducted in three rounds a year that samples Medicare Enrollees using enrollment data to identify respondents and then links their responses to Medicare claims data in order validate self-reported data and to help adjudicate the source of payments for a variety of medical events and services. The claims match process, while simple in the sense that the survey and claims share a beneficiary number, in practice is made complicated by that the claims must be allocated to the correct event at the correct time. This sorting and matching process relies on survey-reported information about the payor or insurer and the health care provider requesting payment to provide initial information for matching. The reliability of survey-reported information clearly rests on the nature of the instrument and the accuracy with which the interviewers report that information. In this paper, we discuss the use of insurance and health care provider lookup functions built into the MCBS CAPI questionnaire that share with the CMS claims files underlying data bases. These lists include the National Plan and Provider Enumeration Sys