Online Microdata Access Solution

Watch the video to learn about the microdata solution

For more information read the Online Microdata Access Brief

Download the ABS Census Dissmination paper A4 Letter

In 2006, the Australian Census counted 20 million people and 7 million households. A total of 116 household and personal questions were asked.

The Australian Bureau of Statistics (ABS) in partnership with Space‐Time Research embarked on an ambitious dissemination strategy for the 2006 Census of Population and Dwellings, one that would provide unprecedented online access to census data. A key aspect of the strategy was the use of on‐the‐fly tabulation to overcome the limits set by pre‐canned reports and data ‘cubes’.

This area outlines the SuperSTAR technology that was used to deliver this census results and describes the various products that were developed to cater the various Census users requirements.

Download the NSO Prosumer Challlgene Conference Paper

National Statistics Offices (NSOs) are under increasing demand to provide greater access to official statistics for their key stakeholders and the public at large. Timely, relevant, and robust statistics are recognised as fundamental economic and social measures of an economy’s performance.

Historically, NSOs have done well in servicing public users with aggregated statistics: however the needs of more demanding users, researchers, policy makers and analysts tend to be met through clumsy data laboratories or expensive custom table production systems.

This group of “Prosumers”, while being small in number, tends to be the greatest user of statistics and the ones who are faced with lack of access to detailed statistics. Hans Rosling from the Gapminder Foundation is considered a quintessential Prosumer. This paper focuses on the rise of Prosumers and the ways in which providers of statistics are beginning to service their needs. We are beginning to see a greater recognition of the role of the Prosumer, who takes statistics and turns them into interesting stories for policy makers.

We will consider the key challenges and opportunities that NSOs face in servicing this evolving market. New confidentiality routines, new Internet based applications allowing users to query Micro-data, faster tabulation engines to cope with large databases and above all an increasing recognition of the role Prosumers play in the statistical value chain removes the barriers associated with servicing Prosumers while still ensuring that the privacy of respondents and integrity of the data is preserved.

Watch the video to learn about the confidentiality solution

Confidentiality

Download the Confidentiality Solution Paper A4 Letter

• On-the-fly table confidentiality.
• In-built routines for low-value cell disturbance or suppression.
• Consequential suppression available.
• Plug-in API for customizable confidentiality routines.
• Background statistics such as top contributors and frequency counts available for use in suppression routines.
• Table auditing facilities available.
• Pre- and post-tabulation rules can be applied.
  
• Permissions to allow privileged users the choice of generating raw data or confidentialized results.

Download the Rounding Methods Paper A4 Letter

Statistical Disclosure Control (SDC) plays a fundamental role in protecting sensitive data whilst minimising information loss. As a field of research, it has existed for decades.

The current trend towards interactive, user-driven, ad hoc queries and the rise of the prosumer market (Ellenberger and Muir 2009) provides additional challenges for the data provider.

Data providers, including National Statistical Offices (NSOs), are still faced with the challenge of minimizing disclosure risk and maximising data useability. However, there is now commonly the additional requirement for techniques that can be applied successfully to ad hoc table generation (for example, online).

We consider some common approaches to disclosure control on both frequency (count) and magnitude data tables. SDC is more usually discussed in terms of census data than survey (which already introduces a degree of protection through survey  participation/membership and weightings) but can be applicable to both.