Local Recoding by Maximum Weight Matching for Disclosure Control of Microdata Sets
We propose "local recoding" as a new technique for controlling disclosure risk of microdata sets. Compared to the technique of global recoding, where the observed values are grouped into broader intervals or categories throughout the data set, in local recoding different grouping is performed for each observation when necessary. As a means of performing local recoding we propose to form pairs of close individuals and recode observed values within each pair. For optimally forming pairs we can employ Edmonds' algorithm (Edmonds(1965)) of maximum weight matching. We illustrate the technique by applying it to the Japanese vital statistics data.
|Date of creation:||Feb 1999|
|Date of revision:|
|Contact details of provider:|| Postal: |
Web page: http://www.cirje.e.u-tokyo.ac.jp/index.html
More information through EDIRC
When requesting a correction, please mention this item's handle: RePEc:tky:fseres:99cf40. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (CIRJE administrative office)
If references are entirely missing, you can add them using this form.