Back to Top

Alternatives to microdata sharing

Are there alternatives to sharing microdata files?

Microdata dissemination implies that the user is offered access to microdata files. Other forms of access to microdata include remote job submission and remote access to microdata, without allowing users direct access. Policy requirements for such access are not covered by our guidelines, but are summarized here with references. Note that these approaches are typically costly and technically demanding.

Job Submission

One approach to allow users to conduct analyses of confidential data involves creating a process that enables them to submit data processing and analysis programs remotely to the data depositor. The user is given a synthetic dataset that replicates the structure and content of the actual datasets. This enables the researcher to develop programs using tools such as SAS, SPSS, or Stata. The programs are then transmitted to the data depositor staff, who run the job against the actual dataset. The results are then vetted for disclosure and returned to the user.

Remote Data Access

Remote data access provides users with access to web-based data tabulation and analysis software, with no possibility of users downloading datasets or generating tables that would reveal individual or small numbers of records. Various software applications are available, mostly commercial (e.g., Nesstar, Beyond 20/20, SuperCross, Redatam, PcAxis, others). Some advanced data centers develop their own applications. For example, the UK Data Archive (UKDA) is piloting a Secure Data Service (SDS) “intended to promote excellence in research by enabling safe and secure remote access by bona fide researchers to data hitherto deemed too sensitive, detailed, confidential or potentially disclosive to be made available under standard licensing and dissemination arrangements.” This approach is satisfactory for tabulations, especially population and housing censuses, but not for advanced analysis.

Engaging a researcher as a temporary staff member

Some data producers provide researchers with access to microdata by engaging them as temporary staff. This makes them subject to the same security provisions as permanent staff of the data producing agency. Such arrangements should be limited to those where the researcher is actually assisting the work of the data producer; otherwise the arrangement could be seen as a sham. (United Nations Economic Commission for Europe [UNECE], Conference of European Statisticians. 2007. “Managing Statistical Confidentiality and Microdata Access: Principles and Guidelines of Good Practice”)