Using Surveys and Administrative Data to Assess the Quality of Linked Data: National Center for Health Statistics’ Data Linkage Program

• Activity Number: 267 - Using Multiple Sources of Data to Assess and Improve Data Quality
• Type: Topic Contributed
• Date/Time: Tuesday, August 4, 2020 : 1:00 PM to 2:50 PM
• Sponsor: Government Statistics Section
• Author(s): Cordell Golden* and Lisa B Mirel
• Companies: National Center for Health Statistics (NCHS/CDC) and National Center Health Statistics (NCHS/CDC)

Abstract

Linking survey data with vital and other administrative data can facilitate richer analyses by augmenting the information collected from the surveys with detailed information on outcomes such as vital status and health care utilization. However, the quality of linked data is only as good as the algorithm used to produce them. The National Center for Health Statistics (NCHS) has a data linkage program that is designed to expand the analytic utility of the Center's health-related surveys. The NCHS Data Linkage Program continually works to enhance their linkage algorithms in efforts to reduce the errors (type I and type II) associated with integrating multiple data sources. This talk will highlight the enhanced linkage methodology that has been implemented as part of the program’s production cycle and will discuss the various approaches that NCHS has used to assess the quality of linked data based on the new algorithm. The assessment has included the use of auxiliary data sources such as follow-up surveys and administrative records. The talk will conclude with a summary of data quality measures that will be included in the documentation of the linked data files.