Summary

This module is about the protection of quantitative tables. Such tables are typically used to release data on business statistics. There are other forms that are sometimes used (such as microdata, frequency tables), but they are not dealt with here. More in particular we shall focus on a single quantitative table together with its marginals. The general case of linked tables (of which the one with hierarchical tables is a special case) is not treated here. A discussion of this case can be found in the literature. References will be provided.

The main issues with protecting quantitative tables are the identification of the unsafe cells in such tables, and how to protect them. Both issues will be addressed here. The one about actually protecting tables is ultimately rather technical, amounting to the solution of often complicated optimisation problems. How this is done is described in the literature, and references will be provided. We concentrate in this module on two techniques: table restructuring and cell suppression.

To read the entire document, please access the pdf file (link under "Related Documents" on the right-hand-side of this page).

Your feedback is appreciated. Please send your remarks, suggestions for improvement, etc. to memobust@cbs.nl.