arXiv subjects

Sallie Ann Keller

Publications and source records attributed to Sallie Ann Keller.

5 recordsLinked to original sources

arXiv2026

The Evolution and Interpretation of "Statistical Purposes"

National Statistical Organizations (NSOs) and other groups often use the term "for statistical purposes only" in communication with prospective respondents, data users and other stakeholders. This term also provides an important anchor for many NSO decisions on operations and ethics. Although public communication often omits a clear operational definition of this term, this paper will show that reviews of underlying laws and policies identify two predominant criteria: (1) production of statistical information about relatively large population aggregates, with the intention of creating a general public benefit; and (2) protection of the confidentiality of data collected about data subjects and a related prohibition against the use of information provided by or about data subjects for legal or regulatory action against those individuals or organizations. We then explore how this term exists, and is often interpreted, within a much broader landscape of legal requirements and of scientific and professional codes of practice, and provide a broader definition for consideration based on these and other ethical frameworks. This paper closes by highlighting several areas that warrant further discussion to better position NSOs to navigate these challenges in the future.

stat.OT↗

arXiv2025

Toward a Principled Framework for Disclosure Avoidance

Responsible disclosure limitation is an iterative exercise in risk assessment and mitigation. From time to time, as disclosure risks grow and evolve and as data users' needs change, agencies must consider redesigning the disclosure avoidance system(s) they use. Discussions about candidate systems often conflate inherent features of those systems with implementation decisions independent of those systems. For example, a system's ability to calibrate the strength of protection to suit the underlying disclosure risk of the data (e.g., by varying suppression thresholds), is a worthwhile feature regardless of the independent decision about how much protection is actually necessary. Having a principled discussion of candidate disclosure avoidance systems requires a framework for distinguishing these inherent features of the systems from the implementation decisions that need to be made independent of the system selected. For statistical agencies, this framework must also reflect the applied nature of these systems, acknowledging that candidate systems need to be adaptable to requirements stemming from the legal, scientific, resource, and stakeholder environments within which they would be operating. This paper proposes such a framework. No approach will be perfectly adaptable to every potential system requirement. Because the selection of some methodologies over others may constrain the resulting systems' efficiency and flexibility to adapt to particular statistical product specifications, data user needs, or disclosure risks, agencies may approach these choices in an iterative fashion, adapting system requirements, product specifications, and implementation parameters as necessary to ensure the resulting quality of the statistical product.

stat.AP↗

arXiv2025

An Approximate Monte Carlo Simulation Method for Estimating Uncertainty and Constructing Confidence Intervals for 2020 Census Statistics

To protect the confidentiality of the 2020 Census, the U.S. Census Bureau adopted a statistical disclosure limitation framework based on the principles of differential privacy. A key component was the TopDown Algorithm, which applied differentially-private noise to an extensive series of counts from the confidential 2020 Census data and transformed the resulting noisy measurements into privacy-protected microdata which were then tabulated to produce official data products. Though the codebase is publicly available, currently there is no way to estimate the uncertainty for statistics included in the published data products that accounts for both the noisy measurements and the post-processing performed within the TopDown Algorithm. We propose an approximate Monte Carlo Simulation method that allows for the estimation of statistical quantities like mean squared error, bias, and variance, as well as the construction of confidence intervals. The method uses the output of the production iteration of the TopDown Algorithm as the input to additional iterations, allowing for statistical quantities to be estimated without impacting the formal privacy protections of the 2020 Census. The results show that, in general, the quantities estimated by this approximate method closely match their intended targets and that the resulting confidence intervals are statistically valid.

stat.ME↗

arXiv2023

An In-Depth Examination of Requirements for Disclosure Risk Assessment

The use of formal privacy to protect the confidentiality of responses in the 2020 Decennial Census of Population and Housing has triggered renewed interest and debate over how to measure the disclosure risks and societal benefits of the published data products. Following long-established precedent in economics and statistics, we argue that any proposal for quantifying disclosure risk should be based on pre-specified, objective criteria. Such criteria should be used to compare methodologies to identify those with the most desirable properties. We illustrate this approach, using simple desiderata, to evaluate the absolute disclosure risk framework, the counterfactual framework underlying differential privacy, and prior-to-posterior comparisons. We conclude that satisfying all the desiderata is impossible, but counterfactual comparisons satisfy the most while absolute disclosure risk satisfies the fewest. Furthermore, we explain that many of the criticisms levied against differential privacy would be levied against any technology that is not equivalent to direct, unrestricted access to confidential data. Thus, more research is needed, but in the near-term, the counterfactual approach appears best-suited for privacy-utility analysis.

cs.CR↗

arXiv2022

Playing catch-up in building an open research commons

On August 2, 2021 a group of concerned scientists and US funding agency and federal government officials met for an informal discussion to explore the value and need for a well-coordinated US Open Research Commons (ORC); an interoperable collection of data and compute resources within both the public and private sectors which are easy to use and accessible to all.

cs.DL↗