Assessing disclosure risk for record linkage
Assessing disclosure risk for record linkage
An intruder seeks to match a microdata file to an external file using a record linkage technique. The identification risk is defined as the probability that a match is correct. The nature of this probability and its estimation is explored. Some connections are made to the literature on disclosure risk based on the notion of population uniqueness.
identification, log-linear model, match, misclassification, uniqueness
9783540874706
166-176
Skinner, Chris
dec5ef40-49ef-492a-8a1d-eb8c6315b8ce
September 2008
Skinner, Chris
dec5ef40-49ef-492a-8a1d-eb8c6315b8ce
Skinner, Chris
(2008)
Assessing disclosure risk for record linkage.
Domingo-Ferrer, Josep and Saygin, Yücel
(eds.)
In Privacy in Statistical Databases.
Springer.
.
(doi:10.1007/978-3-540-87471-3_14).
Record type:
Conference or Workshop Item
(Paper)
Abstract
An intruder seeks to match a microdata file to an external file using a record linkage technique. The identification risk is defined as the probability that a match is correct. The nature of this probability and its estimation is explored. Some connections are made to the literature on disclosure risk based on the notion of population uniqueness.
This record has no associated files available for download.
More information
Published date: September 2008
Venue - Dates:
UNESCO Chair in Data Privacy International Conference, Istanbul, Turkey, 2008-09-24 - 2008-09-26
Keywords:
identification, log-linear model, match, misclassification, uniqueness
Identifiers
Local EPrints ID: 63423
URI: http://eprints.soton.ac.uk/id/eprint/63423
ISBN: 9783540874706
PURE UUID: dbfb5006-3e09-4bd0-bbe0-2e37d6a46c6b
Catalogue record
Date deposited: 24 Oct 2008
Last modified: 15 Mar 2024 11:39
Export record
Altmetrics
Contributors
Author:
Chris Skinner
Editor:
Josep Domingo-Ferrer
Editor:
Yücel Saygin
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