To protect con_dentiality, statistical agencies typically alter data before releasing them to the public. Ideally, the agency would also provide a way for secondary data analysts to assess the quality of inferences obtained with the released data, but this occurs only rarely. Such quality measures can help secondary data analysts to identify inaccurate conclusions resulting from the statistical disclosure limitation procedures, as well as have con_fidence in accurate conclusions. We propose an interactive, web-based system that analysts can query for measures of inferential quality. We identify disclosure risks posed by the system and propose methods for limiting them.
Keywords: Verification server; Statistical disclosure limitation; Data confidentiality; Public use data
Biography: Alan F. Karr is Director of the National Institute of Statistical Sciences (NISS), a position he has held since 2000. He is also Professor of Statistics & Operations Research and Biostatistics at the University of North Carolina at Chapel Hill (since 1993). From 2002 to 2007, he was Associate Director of the Statistical and Applied Mathematical Sciences Institute (SAMSI).
His research activities are cross-disciplinary collaborations involving statistics and such other fields as data confidentiality, data integration, data quality, survey modeling, software engineering, education statistics, transportation, materials science and disease surveillance. He holds one patent and is the author of three books and more than 110 scientific papers, the majority of which have co-authors from other disciplines. Karr is a Fellow of the American Statistical Association and the Institute of Mathematical Statistics, and an elected member of the International Statistical Institute.