Accessing NHANES-CMS Linked Data

Purpose

This module describes the process for obtaining access to the NHANES-CMS linked data.

Task: Describe the Research Data Center (RDC) and Data Request Process

The National Health and Nutrition Examination Survey (NHANES) and Centers for Medicare & Medicaid Services (CMS) linked data files are restricted-use files that can only be accessed through the National Center for Health Statistics (NCHS) Research Data Center (RDC) or the Federal Statistical Research Data Centers (FSRDC), managed by the US Census Bureau. The Federal Statistical Research Data Centers provide access to restricted-use NCHS linked data files through a partnership agreement between NCHS and the US Census Bureau. Additional information about available RDC and FSRDC locations can be found on the NCHS RDC website. To access the NHANES-CMS linked data files, you must submit a proposal to the NCHS RDC. This task will guide you through the NCHS RDC proposal process.

The NHANES-CMS linked data files are restricted-use files that can only be accessed through the NCHS RDC or the FSRDCs. RDCs allow researchers access to individual-level information that is otherwise not available to the public. Researchers interested in analyzing the linked NHANES-CMS restricted-use data files must submit a research proposal to the NCHS RDC for approval. NCHS has published public-use NCHS-CMS feasibility files to help researchers determine whether their intended analytic sample will be of sufficient size to support their research objective prior to developing an RDC proposal.

Information

Restricting user access to the NHANES-CMS linked data files to within the RDC is necessary to protect the privacy of NHANES survey participants and CMS Medicare and Medicaid program beneficiaries. The linked NHANES-CMS data files are subject to the Privacy Act, the Confidential Information Protection and Statistical Efficiency Act, and the Health Insurance Portability and Accountability Act. As such, the information contained on these linked data files is confidential and is to be used only for statistical purposes.

Research Proposal

If you are interested in analyzing the NHANES-CMS linked data files, you must submit a research proposal that outlines the need for this information. The proposal provides a framework for the NCHS RDC staff to understand how the researcher intends to use the data and to identify potential disclosure risks.

Prior to submitting an RDC proposal, researchers should use the publicly available NCHS-CMS feasibility files to determine whether their intended analytic sample will be of sufficient size to support their research objective. The feasibility files are discussed in Module 5 of this tutorial.

All RDC proposals for NHANES and Medicare linked claims data should also include a request for the CMS Master Beneficiary Summary File (MBSF) for the corresponding Medicare coverage year. For example, if you are requesting to analyze Medicare claims data for the period 2010-2013, then your proposal should also include a request for the 2010-2013 MBSF files. The MBSF includes important information on beneficiary Medicare enrollment that is needed to properly construct the analytic sample, particularly to identify Medicare beneficiaries enrolled in a Medicare Part C plan, for whom traditional fee-for-service health care claims are not available. Medicare Part C plans are also referred to as Medicare Advantage (MA) and include Health Maintenance Organizations (HMOs), Managed Care Plans, Preferred Provider Organizations (PPOs), Private Fee-for-Service (PFFS) Plans, Special Needs Plans, and Medicare Medical Savings Account Plans.

All proposals for NHANES and Medicaid linked claims data should also include a request for the CMS Medicaid Person Summary (PS) File for the corresponding Medicaid coverage year. For example, if you are requesting to analyze Medicaid claims data for the period 2010-2012, then your proposal should also include a request for the 2010-2012 Medicaid Person Summary files. The PS file includes important information on Medicaid eligibility and enrollment that is needed to properly construct the analytic sample.

Preparation for Analysis

Start by downloading the public-use NHANES data files you wish to include in your analysis. If you are unfamiliar with the different NHANES datasets, use the continuous NHANES tutorial to learn more about analyzing NHANES data. Because NHANES uses a multi-stage sampling strategy, analyses of NHANES data should account for the weight, cluster, and stratum for each record, as well as the total number of clusters, strata, and records. In order to correctly estimate variance, you should include all observations from every NHANES survey year included in your analysis. More information on the NHANES complex sample design can be found in the NHANES tutorial.

Once you have identified NHANES participants you want to include in your analysis, download the NHANES feasibility files. Merge the feasibility files with the NHANES public-use files using SEQN. Instructions for creating SEQN can be found in the Methodology and Analytic Considerations for the appropriate feasibility file (Medicare or Medicaid).

Once you have confirmed that the linked NHANES-CMS files include the records necessary for your analysis, refer to published guidance for submitting your proposal to the NCHS RDC.

Once the proposal is approved, RDC staff will work with you to create an analytic data file that merges the NHANES public use data you wish to analyze with the linked NHANES-CMS restricted-use data files you requested in your approved RDC proposal. Researchers should follow the NHANES tutorial recommendations for preparing the NHANES public-use files for analysis within the RDC. RDC staff will merge your NHANES public-use files with the restricted-used linked CMS files using SEQN.