Bayesian disclosure risk assessment: predicting small frequencies in contingency tables


Forster, Jonathan J. and Webb, Emily L. (2007) Bayesian disclosure risk assessment: predicting small frequencies in contingency tables , Southampton, GB University of Southampton 21pp. (S3RI Methodology Working Papers, M07/05).

Download

[img] PDF 44611-01.pdf - Author's Original
Download (1MB)

Description/Abstract

We propose an approach for assessing the risk of individual identification in the release of categorical data. This requires the accurate calculation of predictive probabilities for those cells in a contingency table which have small sample frequencies, making the problem somewhat different from usual contingency table estimation, where interest is generally focussed on regions of high probability. Our approach is Bayesian and provides posterior predictive probabilities of identification risk. By incorporating model uncertainty into our analysis, we can provide more realistic estimates of disclosure risk for individual cell counts than are provided by methods which ignore the multivariate structure of the data set.

Item Type: Monograph (Working Paper)
Subjects:
ePrint ID: 44611
Date :
Date Event
28 February 2007Published
Date Deposited: 28 Feb 2007
Last Modified: 16 Apr 2017 18:44
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/44611

Actions (login required)

View Item View Item