Page tree

Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

20.29.    There are a number of software products currently available for managing the confidentiality of microdata[6] and many national statistical offices also develop their own tailored processes and software specific to their legislative requirements.[7]

 

Next: C.4. Users and data dissemination



[1] It may be interesting to note that in the domain of international merchandise trade statistics, “passive confidentiality” is recommended (i.e., data are treated as confidential only when the trader requests so on the grounds that his or her interests would be harmed by the dissemination of their data and the statistical authority finds the request justified based on the confidentiality rules), unless the use of active confidentiality is already the established, desired and accepted practice (see IMTS 2010, para. 10.3);  and  International Merchandise Trade Statistics: Compilers Manual, Revision 1 (IMTS 2010-CM), Studies in Methods, Series F, No. 87/rev.1 (United Nations publication, Sales No. E.13.XVII.8), para. 1.14, available from  http://unstats.un.org/unsd/trade/EG-IMTS/IMTS2010-CM%20-%20white%20cover%20version.pdf.

[2] Eurostat, Handbook on Statistical Disclosure Control: Version 1.2  (2010). Available from http://unstats.un.org/unsd/EconStatKB/Attachment474.aspx.

[3] While three is a common criteria, some statistical agencies use others. For instance, the United Kingdom sets this number at five companies (see United Kingdom, Department of Trade, Enterprise and Investment,  “DETI Confidentiality Statement”, available from  www.detini.gov.uk/data_confidentiality_statement__principle_5_of_the_code_of_practice_for_official_statistics_.pdf).

[4] Eurostat, Handbook on Statistical Disclosure Control: Version 1.2  (2010), para 4.2.1, table 4-1.

[5] Managing Statistical Confidentiality and Microdata Access: Principles and Guidelines of Good Practice (United Nations publication, Sales No. E.07.II.E.7). Available from www.unece.org/fileadmin/DAM/stats/publications/Managing.statistical.confidentiality.and.microdata.access.pdf. .

[6] Special Uniques Detection Algorithm is a system for detecting and grading special uniques. This is needed for confidentializing data sets by first identifying all special unique records and either disguising or removing them. SDCMicro is a free software for the generation of protected microdata for researchers and public use, available at www.ihsn.org/home/software/disclosure-control-toolbox. Country-specific examples of microdata procedures as presented at plenary sessions of the Conference of European Statisticians held by ECE are available from www.unece.org/stats/documents/2013.06.ces.html. More details regarding remote analysis servers can be found in a note by the Australian Bureau of Statistics presented at the sixty-first plenary session of ECE/CES, entitled “Innovative microdata access - confidentiality on the fly” (ECE/CES/2013/29).

[7] For example, a number of national statistical offices release public use files, also referred to as confidentializedu record files (CURFs), which are heavily confidentialized files that remove names, addresses, geographic information and other details. Microdata can also be made available via research data centres or data laboratories, either on-site or through virtual terminals installed in other organizations. Outputs removed from these centres should be checked manually. Finally, some statistical agencies have begun using remote analysis servers, which allow researchers to submit a query via the Internet to the agency’s server, which sends confidentialized output back to the researcher..

 

...