1 / 11

The Process of Practicing Statistical Disclosure Control in Tabular Data at Statistics Sweden

The Process of Practicing Statistical Disclosure Control in Tabular Data at Statistics Sweden. Q2010 Helsinki, May 4-6 Ingegerd Jansson, Michael Carlson, Fredrik Bernström. Recent work at Statistics Sweden. SDC in tables – a common process

betsy
Download Presentation

The Process of Practicing Statistical Disclosure Control in Tabular Data at Statistics Sweden

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. The Process of Practicing Statistical Disclosure Control in Tabular Data at Statistics Sweden Q2010 Helsinki, May 4-6 Ingegerd Jansson, Michael Carlson, Fredrik Bernström

  2. Recent work at Statistics Sweden • SDC in tables – a common process • Handbook on statistical disclosure control for tabular data • Software • Training • Future work

  3. SDC in tables - a common process Damage assessment 1. Disclosure risk assessment No Protection required? Table speci-fication ”Publish” 2. Damage risk assessment Yes Yes Table re-design 4. Utility assessment 3. Protect table Acceptable? No

  4. Handbook on SDC for tabular data The Handbook describes - the common process - preliminaries and some theory - a structure to guide in decision-making The Handbook does not describe - theory in detail (links to ESSNet handbook and other relevant sources) - software in detail

  5. Handbook on SDC for tabular data- a structure to guide in decision-making Four entrances: • Type of table: frequency, magnitude • Type of data: total enumeration, sample survey Frequency tables: • Key variables • Key and target variables Magnitude tables: • Non-negative magnitudes • Negative magnitudes Other aspects where appropriate: type of target object, variable properties, non-response, linked tables, etc

  6. Handbook on SDC for tabular data- a structure to guide in decision-making For each category of tables, the goal is to describe: • Risk scenario • Appropriate methods and parameter values for assessment of risk in table • Appropriate methods and parameter values for protection of table • Implementation and computer aid • Example

  7. Software • So far: τ-Argus, SuperCross and SAS • Project on how to use and incorporate τ-Argus: • evaluate the functionality of τ-Argus with respect to the requirements at Statistics Sweden, i.e. different types of tables and situations (given by the structure of the handbook) • evaluate how to incorporate τ-Argus with the present and planned production system at Statistics Sweden • The goal is that τ-Argus (or any other software) should work smoothly within the production process. This pertains both to technical solutions and to the work process .

  8. PC HTML-report Logfile Outputfile(s) (CSV) .... T-Argus .NET SuperCross Command SAS Metadata Data Software- t-ARGUS and SAS

  9. Training • Statistical methodologist: • two-day introductory course that will be followed up by other types of training • should be able to assist in design, testing and production where necessary • Survey managers/statisticians: • general overview of statistical disclosure control and in particular of the proposed process for SDC

  10. Why are we doing this? • To ensure that protection is actually being carried out where necessary, and that it is being done in a manner that follows best practices • Standardized production → no need to invent the wheel over and over again • Standardized tools → simplified implementation and maintenance • ISO 20252 standard on market, opinion, and social research

  11. Future work • Further development of technical support • Model for continued management • The 2011 Census • Micro data

More Related