An Economic Analysis of Privacy Protection and Statistical Accuracy as Social Choices
MetadataShow full item record
Abowd, John M.; Schmutte, Ian M.
Statistical agencies face a dual mandate to publish accurate statistics while protecting respondent privacy. Increasing privacy protection requires decreased accuracy. Recognizing this as a resource allocation problem, we propose an economic solution: operate where the marginal cost of increasing privacy equals the marginal benefit. Our model of production, from computer science, assumes data are published using an efficient differentially private algorithm. Optimal choice weighs the demand for accurate statistics against the demand for privacy. Examples from U.S. statistical programs show how our framework can guide decision-making. Further progress requires a better understanding of willingness-to-pay for privacy and statistical accuracy.
Any opinions and conclusions are those of the authors and do not represent the views of the Census Bureau, NSF, or the Sloan Foundation. We thank the Center for Labor Economics at UC–Berkeley and Isaac Newton Institute for Mathematical Sciences, Cambridge (EPSRC grant no. EP/K032208/1) for support and hospitality. We are extremely grateful for very valuable comments and guidance from the editor, Pinelopi Goldberg, and six anonymous referees. We acknowledge helpful comments from Robin Bachman, Nick Bloom, Larry Blume, David Card, Michael Castro, Jennifer Childs, Melissa Creech, Cynthia Dwork, Casey Eggleston, John Eltinge, Stephen Fienberg, Mark Kutzbach, Ron Jarmin, Christa Jones, Dan Kifer, Ashwin Machanavajjhala, Frank McSherry, Gerome Miklau, Kobbi Nissim, Paul Oyer, Mallesh Pai, Jerry Reiter, Eric Slud, Adam Smith, Bruce Spencer, Sara Sullivan, Salil Vadhan, Lars Vilhuber, Glen Weyl, and Nellie Zhao, along with seminar and conference participants at the U.S. Census Bureau, Cornell, CREST, George Mason, Georgetown, Microsoft Research–NYC, University of Washington Evans School, and SOLE. William Sexton provided excellent research assistance. No confidential data were used in this paper. Supplemental materials available at http://doi.org/10.5281/zenodo.1345775. The authors declare that they have no relevant or material financial interests that relate to the research described in this paper.
This work received support from Alfred P. Sloan Foundation Grant G-2015-13903; NSF Grants SES-1131848, BCS-0941226, and TC-1012593.
statistics, privacy, data
Attribution-NonCommercial-ShareAlike 4.0 International
The following license files are associated with this item:
Except where otherwise noted, this item's license is described as Attribution-NonCommercial-ShareAlike 4.0 International