Generating Synthetic Family Income for the Consumer Expenditure Surveys

Have you ever filled out surveys and worried about your submitted personal information not being protected? Such worries are sensible and legitimate, as researchers have demonstrated great risks associated with personal-level data released to the public. In this talk, Dr. Hu will introduce synthetic data, an approach to data dissemination which provides good data utility and sufficient privacy protection. In particular, Dr. Hu will present a novel risk-efficient synthesis model, that factors a record’s disclosure risk into the Bayesian data synthesis for privacy protection. Dr. Hu will demonstrate the method with an application to the Consumer Expenditure Surveys of the U.S. Bureau of Labor Statistics.