MAX and Survey Linkages

Issue Briefs and Reports

MAX and NCHS Survey Linkage Design Report (PDF).  CMS was interested in linking MAX files with survey data, including four surveys conducted by the National Center for Health Statistics (NCHS)—the National Health Interview Survey (NHIS), the National Health and Nutrition Examination Survey (NHANES), the Second Longitudinal Study of Aging (LSOA II), and the National Nursing Home Survey (NNHS). In linking the MAX files to the NCHS survey data, CMS can combine the best source of data on Medicaid services with the best sources of data on health status and risk factors. The combined files can be extraordinarily valuable to researchers conducting comparative effectiveness research as well as to the wider health research community. CMS contracted with Mathematica to link the NCHS data to MAX data for 1999-2011. This report describes the linkage software previously developed by CMS and recommends minor modifications to the design and implementation of that software.

MAX and NCHS Survey Linkage, 1999-2009 (PDF). This report focuses on the linking of an extract of National Center for Health Statistics (NCHS) survey data to the Medicaid Analytic eXtract (MAX) files. It describes the data sources, presents the linkage algorithm, examines the linkage results, and offers advice to researchers interested in using the linked NCHS-MAX files.

Using the MAX-NHANES Merged Data to Evaluate the Association of Obesity and Medicaid Costs (PDF). This issue brief presents the results of the first study conducted using the merged MAX-NHANES data. Using data from MAX-NHANES 1999-2004, we assessed the association of obesity on annual total fee-for-service Medicaid costs. While the estimated costs were higher for obese adults than non-obese adults, the differences in costs by obesity status were not significant at the 0.05 level. The results of the analysis demonstrate the hazard of using a small national survey (NHANES) with a state-based data system (MAX) to perform cost analyses, particularly when the range of realistic costs is large. 

A report (PDF) is available on the MAX and the Medicare Current Beneficiary Survey (MCBS) linkage activities. In the report, we detail the method used to link Medicare survey data from the Medicare Current Beneficiary Survey (MCBS) with Medicaid administrative data from the Medicaid Analytic eXtract (MAX) files, and assess the quality of the linked MCBS-MAX records. Although the MCBS contains information on all services covered by Medicare, it does not contain any information on benefits—particularly long-term care services—that are covered only by Medicaid. And although we can see service usage in MAX, the only health status information available in the data is based on the diagnosis codes for Medicaid-financed services. MCBS has information on the health conditions, health-related behaviors, and health status of enrollees, such as activities of daily living (ADLs) and instrumental activities of daily living (IADLs). By linking the MCBS and MAX data, researchers can obtain a more complete picture of total Medicare and Medicaid expenditures for and service utilization by dually-enrolled beneficiaries, and get valuable insight into the health status of these dual enrollees.