Disclosure Control Methods and Information Loss for Microdata

Statistical disclosure control (SDC) seeks to modify statistical data so that they can be published without giving away confidential information that can be linked to specific respondents. The challenge for SDC is to achieve this modification with minimum loss of the detail and accuracy sought by database users. SDC methods for microdata are usually known as masking methods, of which there is a wide range. From the point of view of their operational principles, current masking methods fall into the following two categories (Willenborg and De Waal 2001): • Perturbative. The microdata set is distorted before publication. In this way, unique combinations of scores in the original dataset may disappear and new unique combinations may appear in the perturbed dataset; such confusion is beneficial for preserving statistical confidentiality. The perturbation method used should be such that statistics computed on the perturbed dataset do not differ significantly from the statistics that would be obtained on the original dataset. • Nonperturbative. Nonperturbative methods do not alter data; rather, they produce partial suppressions or reductions of detail on the original dataset. Global recoding, local suppression, and sampling are examples of nonperturbative masking.