Individual risk estimation in μ-Argus: a review

When microdata files for research are released, it is possible that external users may attempt to breach confidentiality. For this reason most National Statistical Institutes apply some form of disclosure risk assessment and data protection. Building on previous work by Benedetti and Franconi (1998), the paper describes statistical methods for the estimation of record-level disclosure risk measures. These permit the identification of unsafe records to be protected by disclosure limitation techniques. The paper reviews the main aspects of the individual risk methodology as implemented by CBS Netherlands in cooperation with the Authors in the software Mu-Argus. Such an approach defines measures of risk for protection of files of independent records as well as hierarchical files. The theory and some practical issues such as threshold setting are discussed in both cases.