Abstract

Policymakers often rely on official statistics and administrative data to make essential public policy decisions, such as using administrative tax data to broaden our understanding of individuals’ and firms’ responses to economic incentives through quantitative research. However, direct access to federal confidential data is limited to a select few researchers. Recently, privacy researchers and policymakers proposed using formally private validation servers to provide another tier of access, but little is known about the expectations and needs of data users for such a system—much less their knowledge and perceptions of formal privacy methods for noise infusion. To evaluate and identify the expectations and needs of potential users, we conduct a convenience sample survey of members of the American Economic Association (AEA). We find that economists overall have a low awareness of DP, and among those who have an opinion about DP, they are critical about the noise being added. But, the same economists are divided on the need for the offered privacy protections. In regards to a validation server, our results help better understand the types of statistical methods that are most useful to economists, and how the injection of noise under DP would affect the value of accessing administrative data in this framework. We provide suggestions for how the adoption of differentially private methods and tools can align with users’ expectations, possible next steps to create better privacy-preserving tools for the economics community, and recommendations to improve the development of formally private tools.

Keywords: administrative data, data confidentiality, data privacy, differential privacy, social science, tax policy analysis

08/21/2024: To preview this content, click below for the Just Accepted version of the article. This peer-reviewed version has been accepted for its content and is currently being copyedited to conform with HDSR’s style and formatting requirements.

©2024 Aaron R. Williams, Joshua Snoke, Claire McKay Bowen, and Andres Felipe Barrientos. This article is licensed under a Creative Commons Attribution (CC BY 4.0) International license, except where otherwise indicated with respect to particular material included in the article.