Data quality in the National Hospital Discharge Survey - ARCHIVED

Articles and reports: 11-522-X20010016284

Description:

This paper discusses in detail issues dealing with the technical aspects of designing and conducting surveys. It is intended for an audience of survey methodologists.

Since 1965, the National Center for Health Statistics has conducted the National Hospital Discharge Survey (NHDS), a national probability sample survey of discharges from non-federal, short-stay and general hospitals. A major aspect of the NHDS redesign in 1988 was to use electronic data from abstracting service organizations and state data systems. This paper presents an overview of the development of the NHDS and the 1988 redesign. Survey methodologies are reviewed in light of the data collection and processing issues arising from the combination of "manually" abstracted data and "automated" data. Methods for assessing the overall quality and accuracy of the NHDS data are discussed for both data collection modes. These methods include procedures to ensure that incoming data meet established standards and that abstracted data are processed and coded according to strict quality control procedures. These procedures are presented in the context of issues and findings from the broader literature about the quality of hospital administrative data sets.

Issue Number: 2001001
Author(s): McLemore, Thomas; Pokras, Robert
FormatRelease dateMore information
CD-ROMSeptember 12, 2002
PDFSeptember 12, 2002