Creation of Public Use Files: Lessons Learned from the Comparative Effectiveness Research Public Use Files Data Pilot Project

• 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): Erkan Erdem* and Sergio Prada*+
• Companies: IMPAQ International LLC
• Keywords: Public use files ; re-identification ; de-identification ; Medicare claims ; comparative effectiveness research ; data utility

Abstract

In this paper we describe lessons learned from the creation of Basic Stand Alone (BSA) Public Use Files (PUFs) for the Comparative Effectiveness Research Public Use Files Data Pilot Project (CER-PUF). CER-PUF is aimed at increasing access to the Centers for Medicare and Medicaid Services (CMS) Medicare claims datasets through PUFs that: do not require user fees and data use agreements, have been de-identified to assure the confidentiality of the beneficiaries and providers, and still provide substantial analytic utility to researchers. For this paper we define PUFs as datasets characterized by free and unrestricted access to any user. We derive lessons learned from five major project activities: (i) a review of the statistical and computer science literature on best practices in PUF creation, (ii) interviews with comparative effectiveness researchers to assess their data needs, (iii) case studies of PUF initiatives in the United States, (iv) interviews with stakeholders to identify the most salient issues regarding making microdata publicly available, and (v) the actual process of creating the Medicare claims data BSA PUFs.