A Unified Mathematical Programming Framework for Different Statistical Disclosure Limitation Methods

Abstract

This paper concerns statistical disclosure control methods to minimize information loss while keeping small the disclosure risk from different data snoopers. This issue is of primary importance in practice for statistical agencies when publishing data. It is assumed that the sensitive data have been identified by practitioners in the statistical offices, and the paper addresses the secondary problem of protecting these data with different methods, all defined in a unified mathematical framework. A common definition of protection is used in four different methodologies. Two integer linear programming models described in the literature for the cell suppression methodology are extended to work also for the controlled rounding methodology. In addition, two relaxed variants are presented using two associated linear programming models, called partial cell suppression and partial controlled rounding, respectively. A final discussion shows how to combine the four methods and how to implement a cutting-plane approach for the exact and heuristic resolution of the combinatorial problems in practice. This approach was implemented in ARGUS, a software package of disclosure limitation tools.