skip to content

Data linkage and anonymisation

Participation in INI programmes is by invitation only. Anyone wishing to apply to participate in the associated workshop(s) should use the relevant workshop application form.

4th July 2016 to 21st December 2016
Chris Skinner
Peter Christen Australian National University
Stephen Fienberg
David Hand
Robin Mitra
Natalie Shlomo University of Manchester

Programme Theme

Public policy decisions and much scientific research hinge on accurate and comprehensive data about people. Commercial organisations base their success similarly on data describing how people behave. To support such exercises, increasing numbers of large databases describing people, their characteristics and their behaviour are being looked to for analysis. The opportunities afforded by linking different databases are of particular current interest. There is often, however, a tension between sharing the information in such databases so that public and private benefit can be gained from combining and analysing them, whilst at the same time protecting privacy and confidentiality for the individuals who make up the databases. In principle, one might hope to address this tension by anonymising the data to remove threats to privacy, whilst preserving the analytic value of the data. Experience shows, however, that such anonymisation is not so simple. The focus of this programme will be on contributions the mathematical sciences can make to enhancing opportunities for the analysis of data, especially obtained through linkage, whilst protecting privacy and taking account of related practical constraints.

A basic purpose of the programme will be to foster exchange between different parts of the mathematical sciences where these themes are being addressed in different ways, especially in statistics and computer science, as well as between researchers investigating data linkage and privacy protection, topics which have often been considered separately. More broadly, the programme will seek to promote exchange between the mathematical sciences and related disciplines, such as economics, as well as with practitioners and domain experts on the front line of enabling access to large databases: for example in official statistics, medical research and commerce. The programme will include five events designed to promote interchange between these different communities as well as to open these themes up to a wider spectrum of researchers in the mathematical sciences, including those at early career stages.

University of Cambridge Research Councils UK
    Clay Mathematics Institute London Mathematical Society NM Rothschild and Sons