Nuts and Bolts of Preparing a System for Summarizing Medicare Beneficiaries

• Activity Number: 332
• Type: Topic Contributed
• Date/Time: Tuesday, August 2, 2011 : 10:30 AM to 12:20 PM
• Sponsor: Section on Health Policy Statistics
• Author(s): Al Crego*+ and Tzy-Chyi Yu and Joshua Michael Borton and Peter K. Kwok
• Companies: NORC at the The University of Chicago and NORC at the The University of Chicago and NORC at the The University of Chicago and NORC at the The University of Chicago
• Keywords: Medicare claims ; beneficiary-level information ; processing techniques

Abstract

Some CER needs having been determined to be at the level of unique beneficiaries, the challenge was to implement a summary system that was accurate, reproducible, yielded files in forms optimal for treatment procedures, and simultaneously served potential research needs. This was accomplished for two random, five-percent samples of 2008 Medicare beneficiaries. Sufficient flexibility was also necessary to accommodate changes to perceived or future research goals. We began with two databases, each comprised of over three-thousand variables and over one-hundred million records across various files, and developed a processing stream that could be applied, with minimal changes, to any number of similar databases, resulting in tractable summary files. In doing so, we applied industry-standard summary techniques in multiple dimensions, dependent on claims and beneficiary-level information.