for the NSF-Census-IRS Workshop on Synthetic Data and Confidentiality Protection 2009
The final print program (with some minor post-workshop typographic corrections) can be found here (last updated 2009-09-24). Further information on the workshop can be found on the main page. Presentations are listed below, with links to the actual presentation document.
Opening remarks
- Tom Mesenbourg, Deputy Director of the U.S. Census Bureau
- John Abowd (Cornell University)
Session 1: : Imputation methods and synthesizers
- Jerry Reiter: Easily implemented, nonparametric synthesizers based on algorithmic methods in computer science (additional tables)
- Gary Benedetto and Simon Woodcock: Partially-synthetic linked employer-employee data
- Robert Creecy: The Feasibility of Creating a Fully Synthetic Decennial Census Microdata File
- Michael Larsen and Jennifer Huckett: Synthetic data methods using quantile regression and hot deck with rank swapping
- John Abowd, Fredrik Andersson, Matthew Graham, Lars Vilhuber and Jeremy Wu: Formal Privacy Guarantees and Analytical Validity of OnTheMap Public-use Data
Session 2: Synthetic data in public use micro-data products
- Martha Stinson, Gary Benedetto, and Melissa Bjelland: Summary of Methods and Preliminary Assessment of the SIPP Synthetic Beta
- Saki Kinney: Synthetic Longitudinal Business Database
- Jörg Drechsler: New Data Dissemination Approaches in Old Europe – Synthetic Datasets for a German Establishment Survey
- Sam Hawala and Rolando Rodriguez: Disclosure avoidance for group quarters in the American Community Survey: Details of the synthetic data method
- Trivellore Raghunathan: Diagnostic Tools for Assessing Validity of Synthetic Data Inferences
Session 3: Synthetic data and disclosure avoidance
- Arnold Reznek: Disclosure avoidance issues at the Census Bureau
- Stefan Bender: Pulling wool over users' eyes
- Nick Greenia: Confidentiality Issues with Tax Data
- Jennifer Madans: Disclosure avoidance issues at NCHS
Closing remarks
- Donald Rubin (Harvard University)
Funding for the conference and its preparation were provided by National Science Foundation (NSF) Grant SES-0922494, the U.S. Census Bureau's Center for Economic Studies, the Internal Revenue Service (IRS), and the Edmund Ezra Day Professorship at Cornell University.
