Data swapping; Rank swapping
Data swapping was originally designed by Dalenius and Reiss  as a masking method for statistical disclosure control of databases containing only categorical attributes. The basic idea behind the method is to transform a database by exchanging values of confidential attributes among individual records. Records are exchanged in such a way that low-order frequency counts or marginals are maintained.
Rank swapping is a variant of data swapping [2, 3]. First, values of an attribute Xi are ranked in ascending order, then each ranked value of Xi is swapped with another ranked value randomly chosen within a restricted range (e.g., the rank of two swapped values cannot differ by more than p% of the total number of records, where p is an input parameter). This algorithm is independently used on each original attribute in the original data set.
It is reasonable to expect that multivariate statistics computed from data swapped with...
- 1.Dalenius T, Reiss SP. Data-swapping: a technique for disclosure control (extended abstract). In: Proceedings of the ASA Section on Survey Research Methods; 1978. p. 191–4.Google Scholar
- 2.Domingo-Ferrer J, Torra V. A quantitative comparison of disclosure control methods for microdata. In: Doyle P, Lane JI, Theeuwes JJM, Zayatz L, editors. Confidentiality, disclosure and data access: theory and practical applications for statistical agencies. Amsterdam: North-Holland; 2001. p. 111–34.Google Scholar
- 3.Hundepool A, Van de Wetering A, Ramaswamy R, Franconi F, Polettini S, Capobianchi A, De Wolf P-P, Domingo-Ferrer J, Torra V, Brand R, Giessing S. μ-Argus user’s manual version 4.1, February 2007.Google Scholar