Collaborating with experts to explore advancements in privacy and data confidentiality methods
Today, the Quality Centre in the Best Practice and Impact Division published the National Statistician’s Quality Review (NSQR) of Privacy and Data Confidentiality Methods to support producers of statistics to think strategically about the methods needed to keep pace with changing data sources and technologies. This NSQR outlines the challenges faced and sets out the steps that should to be taken across the statistical system.
The review is the culmination of an extensive collaboration between experts from across academia, the private sector, the Office for National Statistics (ONS), wider GSS and other National Statistical Institutes (NSIs). When we initially proposed this first NSQR to GSS Heads of Professions in December last year, it received a lot of interest and was welcomed as an important but difficult area to review. This is the first NSQR conducted in a new format, covering a topic deemed a priority for the whole statistical system and involving experts from across sectors to identify new and emerging challenges.
Privacy and confidentiality are complex and fast evolving areas of research. Intruder attacks pose an increasing threat exacerbated by technological developments and an increasing availability of additional data sources that make re-identification easier. On one hand, the producers of statistics face increasing pressure to be more transparent regarding the approaches they use, while on the other hand they are required to ensure privacy and data confidentiality and engender trust. Throughout all this, they also need to be focused on user needs and make sure that the users have sufficiently detailed data to inform policy decisions.
We are taking a leading role in developing these methods and ensuring the methods used are not only fit for purpose but among some of the best in the world. This includes sharing knowledge with experts, building expertise and supporting statistical producers with advice and guidance on the most up to date methods.
This NSQR was conducted in close collaboration with Keith Spicer, the head of the ONS Statistical Disclosure Control and his team of experts: Stephanie Blanchard, Iain Dove, Christos Ntoumos, Peter Youens, Philip Lowthian and Jason Graves. I am indebted to Keith and his team for their hands-on help and advice throughout this process and the numerous discussions on the complexities and challenges encountered when trying to translate theory into practice.
The work also gave me the opportunity to collaborate with leading experts in privacy and confidentiality external to GSS, and strengthen our partnerships with them.
Working on this NSQR I have learned something new every day, as I tried to get my head around emerging concepts and the different relationships between them without losing sight of the bigger picture and the purpose. Collaborations were instrumental in helping guide the content of the contributed articles, identify new areas where further development was needed and bridging the gap between what is theoretically possible and what is practical in a statistical context.
A highlight was organising the GSS Methodology Advisory Committee event, “Privacy and Data Confidentiality Methods Joining Forces”. Chaired by Sarah Henry, director of Methods Data Research, the meeting brought together around 60 leading experts in these methods from across the world. It was insightful having the contributing authors and experts from across GSS and other NSIs in the same room discussing and debating some of the key issues being tackled at the moment, agreeing on some and disagreeing on others.
To mention just a few, we were pleased to have the experts from the Australian Bureau of Statistics dialling in via video conference and contributing to the discussions throughout the day despite the unsocial hour in Australia. Collaborating with experts from other NSIs is at the heart of this NSQR, as statistical institutes are facing similar challenges it makes perfect sense to work together to identify solutions.
This is not the end! We are establishing a GSS Task Force in January 2019 to further develop collaborations across GSS and wider.