Synthesizing Truncated Count Data for Confidentiality

• Activity Number: 478
• Type: Topic Contributed
• Date/Time: Wednesday, August 7, 2013 : 8:30 AM to 10:20 AM
• Sponsor: Survey Research Methods Section
• Author(s): Sam Hawala*+ and Jerry Reiter and Quanli Wang
• Companies: US Census Bureau and Duke University and Duke University
• Keywords: Disclosure Limitation ; Confidentiality ; Truncated Poisson Distribution ; Synthetic Data ; Hierarchical Bayesian Model ; Tabular Data

Abstract

To maintain confidentiality national statistical agencies traditionally do not include small counts in publicly released tabular data products. They typically delete these small counts, or combine them with counts in adjacent table cells to preserve the totals at higher levels of aggregation. In some cases these suppression procedures result in too much loss of information. To increase data utility and make more data publicly available, we propose to generate synthetic values for the small counts from a Bayesian hierarchical model. We do not disturb the counts in the data tables that were considered safe. We also discuss how the same model allows for computation of several disclosure risk measures.