Redesign of the Medicare Current Beneficiary Survey (MCBS) Sample

• Activity Number: 255
• Type: Contributed
• Date/Time: Tuesday, August 13, 2002 : 2:00 PM to 3:50 PM
• Sponsor: Section on Survey Research Methods*
• Author(s): Annie Lo*+ and Adam Chu and Richard Apodaca
• Affiliation(s): Westat, Inc. and Westat, Inc. and Westat, Inc.
• Keywords: Multistage probability sample ; resampling methods ; overlap maximization ; longitudinal sample ; rotating panels ; Medicare population

Abstract

The Medicare Current Beneficiary Survey (MCBS) conducted by the Centers for Medicare and Medicaid Services (CMS) is a continuous panel survey of Medicare beneficiaries that collects comprehensive data on health status, source of care, health care utilization and costs, satisfaction with health care, and other topics. Since its inception in 1991, the MCBS has employed a multistage stratified sampling design, where the first-stage sample is a nationally representative sample of geographical areas referred to as primary sampling units (PSUs). The MCBS also employs a rotating panel design where new samples of beneficiaries are selected annually. The new sample is always selected from the same set of PSUs. Over time, the use of the same PSUs can adversely affect both sampling precision and operational efficiency. To counter potential losses in efficiency, a decision was made in 2000 to redesign the MCBS PSU sample. This paper summarizes the procedures used to select the new PSU sample. In order to limit the operational disruption inherent in moving to a new PSU sample, the overlap with existing PSUs was maximized using techniques developed by Ernst (1986).