When Privacy Protection Goes Wrong: How and Why the 2020 Census Confidentiality Program Failed

Author:

Ruggles Steven1

Affiliation:

1. Steven Ruggles is Regents Professor of History and Population Studies, University of Minnesota, and Director of IPUMS, both in Minneapolis, Minnesota. .

Abstract

The U.S. Census Bureau implemented a new disclosure control strategy for the 2020 Census that adds deliberate error to every population statistic for every geographic unit smaller than a state, including metropolitan areas, cities, and counties. This article traces the evolving rationale for the new procedures and assesses the impact of the 2020 disclosure control on data quality. The Census Bureau argues that the traditional disclosure controls used for the 2010 and earlier censuses revealed the confidential responses of millions of Americans. I argue that this claim is unsupported, and that there is no evidence that anyone's responses were compromised. The new disclosure control strategies introduce unnecessary error with no clear benefit; in fact, the new procedures may actually be less effective for protecting confidentiality than the procedures they replaced. I conclude with recommendations for minimizing disclosure risk while maximizing data utility in future censuses.

Publisher

American Economic Association

Reference114 articles.

1. Abowd, John M. 2017. "Research Data Centers, Reproducible Science, and Confidentiality Protection:

2. The Role of the 21st Century Statistical Agency." Presentation, Summer DemSem, Wisconsin Federal Statistical RDC, June 5, 2017. https://www2.census.gov/cac/sac/meetings/2017-09/role

3. statistical-agency.pdf. Abowd, John M. 2018a. "Staring-Down the Database Reconstruction Theorem." Presentation, Joint

4. Statistical Meetings, Vancouver, BC, July 30, 2018. https://www.census.gov/content/dam/Census/

5. newsroom/press-kits/2018/jsm/jsm-presentation-database-reconstruction.pdf. Abowd, John M. 2018b. "The U.S. Census Bureau Adopts Differential Privacy." Speech, 24th ACM

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3