Statistical Disclosure Control Based on Random Uncertainty Intervals
In this paper we propose a statistical framework for controlling the risk in disclosing public micro-data. The idea is to replace the micro-data by controllable quasi-data represented as uncertainty intervals. An uncertainty interval is an interval covering a genuine datum with specified probability. We also discuss statistical inferences based on random intervals. Problems discussed include point and interval estimation of the mean, two-sample tests and density estimations.
KeywordsHausdorff Distance Uncertainty Interval Random Interval Artificial Data Uncertainty Level
Unable to display preview. Download preview PDF.
- 2.Giné, E. Hahn, M.G. and Zinn, J. (1985). Limit Theorems for Random Sets, Lecture Notes in Mathematics 990, 112–135, Springer, New York.Google Scholar
- 8.Willenborg, L. and Waal, T. (1996). Statistical Disclosure Control in Practice, Lecture Notes in Statistics 111, Springer, New York.Google Scholar
- 9.Willenborg, L. and Waal, T. (2000). Elements of Statistical Disclosure Control, Springer, New York.Google Scholar