Abstract

Abstract: Per-record measures of disclosure risk have potential uses in
statistical disclosure control programs as a means of identifying sensitive
or atypical records in public-use microdata files. A measure intended for
sample data based on the Poisson-inverse Gaussian distribution and
overdispersed log-linear modeling is presented. An empirical example
indicates that the proposed model performs approximately as well as the
Poisson-lognormal model of Skinner and Holmes (1998) and may be a tractable
alternative as the required computational effort is significantly smaller.
It is also demonstrated how to extend the application to take into account
population level information. The empirical results indicate that using
population level information sharpens the risk measure.

Keywords: Disclosure control; Log-linear models; Poisson-inverse Gaussian;
Risk-per-record; Uniqueness.

Michael Carlson, Department of Statistics, Stockholm University,
SE-106 91 Stockholm, Sweden. E-mail: Michael.Carlson@stat.su.se