A Real-Time Online System for Analyzing Restricted Data from the U.S. National Center for Health Statistics' National Health Interview Survey
Jane F. Gentleman
Division of Health Interview Statistics, U.S. National Center for Health Statistics, Hyattsville, MD, United States

The National Health Interview Survey (NHIS) has monitored the health of the United States noninstitutionalized civilian population since 1957. It is conducted by the National Center for Health Statistics (NCHS), which is the United States' official health statistics agency. NHIS data on a broad range of health topics are collected through personal household interviews. Public use microdata files are released annually, 6 months after the data collection year. Data users can currently perform analyses of NHIS data by (1) downloading public use NHIS microdata from the NCHS Website; (2) for data years for which public use files have already been released, accessing selected restricted NHIS microdata via the NCHS Research Data Center (RDC), under controlled conditions to protect data confidentiality; (3) accessing preliminary quarterly microdata files available in the RDC during the year before release of the final microdata files. However, users of these three options must program their own analyses. To provide additional services, NCHS is developing two new real-time online analytic systems that will perform user-directed analyses of NHIS data. “System P” will analyze only public use microdata. “System R” will also analyze selected restricted NHIS variables. NCHS is working with contractors to develop rigorous confidentiality screening methods for System R that will meet NCHS' high standards for disclosure avoidance. System R will utilize a cocktail of disclosure avoidance techniques. System R will focus on helping meet demands for state-level NHIS estimates. Currently, analysts must use the RDC to access NHIS state identifiers; this requires submitting a research proposal and paying a user fee. System R will provide rapid, convenient access to state-level estimates and reduce and/or delay the need to use the RDC.

Keywords: National health interview survey; U.S. National Center for Health statistics; Disclosure avoidance for survey data; Confidentiality

Biography: Since 1999, Jane F. Gentleman has been the Director of the division that conducts the National Health Interview Survey at the U.S. National Center for Health Statistics. Before that, she worked at Statistics Canada and, before that, at the University of Waterloo in Canada, from which she received a Ph.D. in Statistics. She is an elected member of the ISI and a Fellow of the American Statistical Association (ASA). She has been very active in professional statistical societies, including being President of the Statistical Society of Canada, Vice President of the ASA, and President of the U.S. Caucus for Women in Statistics.