Key points
- The National Center for Health Statistics (NCHS) linked data resources can be used for public health research and disease surveillance.
- NCHS creates public-use feasibility files to improve access to linked data.
- Find information about public-use linked data files and how to request access to restricted-use linked data files.
Overview
The National Center for Health Statistics (NCHS) Data Linkage Program creates public-use and restricted-use linked data files to support public health research and disease surveillance.
- New public-use synthetic linked files have been created to improve access to NCHS linked data.
- Public-use mortality (death) files have been created for the National Health Interview Survey (NHIS) and the National Health and Nutrition Examination Survey (NHANES).
- Restricted-use data files are produced for all sources of NCHS linked administrative data. These files are available through the NCHS Research Data Center network.
- Public-use linked Medicare feasibility files help researchers determine whether restricted-use linked data are appropriate for their research.
Using NCHS linked data
NCHS has created publicly available synthetic linked data to increase access to NCHS data. The new synthetic linked data files are created using statistical techniques that attempt to maintain as many properties of the original linked data as possible while protecting the privacy of NCHS survey respondents.
NCHS has created a verification process so that researchers can confirm synthetic linked data results against the original linked data.
Public-use Linked Mortality Files (LMF) are available for NHIS and NHANES. The Public-use LMFs include a limited set of mortality variables for adult survey participants. Linking survey participant data with NDI mortality (death) data allows researchers to conduct outcome studies to investigate the connection between different health factors and death.
Some information in the public-use LMFs was changed to keep survey participants' identities safe. For certain records, the follow-up time or underlying cause of death were substituted with synthetic values. Information about whether a person is alive or dead was not changed.
Restricted-use linked data contain detailed information from administrative data sources and can be merged with NCHS survey data. Restricted-use data are accessible only through the NCHS Research Data Center (RDC) network for approved research projects.
Researchers can use feasibility files to understand whether restricted-use data will be appropriate for their research.
Combining data sources
Restricted-use linked data files may be combined across the different administrative data sources, for example Medicare and mortality. However, combining the public-use linked mortality files with the restricted-use linked mortality data is not allowed within the RDC.
The public-use synthetic linked data files cannot be combined with other public-use or restricted-use linked data.