Releasing microdata: disclosure risk estimation, data masking and assessing utility
Releasing microdata: disclosure risk estimation, data masking and assessing utility
Statistical Agencies need to make informed decisions when releasing sample microdata from social surveys with respect to the level of protection required in the data and the mode of access. These decisions should be based on objective quantitative measures of disclosure risk and data utility. This paper reviews recent developments in disclosure risk assessment and discusses how these can be integrated with established methods of data masking and utility assessment for releasing microdata. We illustrate the Disclosure risk-Data Utility approach based on samples drawn from a Census where the population is known and can be used to investigate sample-based methods and validate results.
log-linear models, measurement error, additive noise, micro-aggregation, random rounding, pram, information loss
Southampton Statistical Sciences Research Institute, University of Southampton
Shlomo, Natalie
e749febc-b7b9-4017-be48-96d59dd03215
11 February 2009
Shlomo, Natalie
e749febc-b7b9-4017-be48-96d59dd03215
Shlomo, Natalie
(2009)
Releasing microdata: disclosure risk estimation, data masking and assessing utility
(S3RI Methodology Working Papers, M09/02)
Southampton, UK.
Southampton Statistical Sciences Research Institute, University of Southampton
15pp.
Record type:
Monograph
(Working Paper)
Abstract
Statistical Agencies need to make informed decisions when releasing sample microdata from social surveys with respect to the level of protection required in the data and the mode of access. These decisions should be based on objective quantitative measures of disclosure risk and data utility. This paper reviews recent developments in disclosure risk assessment and discusses how these can be integrated with established methods of data masking and utility assessment for releasing microdata. We illustrate the Disclosure risk-Data Utility approach based on samples drawn from a Census where the population is known and can be used to investigate sample-based methods and validate results.
Text
65423-01.pdf
- Author's Original
More information
Published date: 11 February 2009
Keywords:
log-linear models, measurement error, additive noise, micro-aggregation, random rounding, pram, information loss
Identifiers
Local EPrints ID: 65423
URI: http://eprints.soton.ac.uk/id/eprint/65423
PURE UUID: dd1a03d7-4bbe-41cb-9c15-3a364d40244a
Catalogue record
Date deposited: 12 Feb 2009
Last modified: 13 Mar 2024 17:38
Export record
Contributors
Author:
Natalie Shlomo
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics