New Research Explores Modeling Approaches to Quantifying Disclosure Risk

Key diagnostics can strengthen the measurement of disclosure risk relating to sensitive information in modern data environments, according to a recent article coauthored by Westat experts and published in Transactions on Data Privacy. In “Issues in Estimating Reidentification Risk Using Log-Linear Models in Complex Survey Samples,” the authors, including Westat’s Lin Li, MS, and Tom Krenzke, MS, analyze modeling techniques for quantifying disclosure risk, evaluate their effectiveness under realistic conditions, and outline practical considerations for organizations seeking to estimate and reduce disclosure risks while maintaining data utility.

This study’s findings are particularly important as agencies and researchers increasingly rely on complex datasets to inform policy and program evaluation. “Advances in disclosure risk assessment methods are essential to ensuring that high-quality data can be used and shared with the public responsibly,” Li notes, emphasizing the growing need for tools that support valid analyses of disclosure risk.

This research contributes to the broader field of data privacy protection, demonstrating Westat’s commitment to supporting evidence-based decision-making while maintaining data privacy.