Skip to main content

Research Repository

Advanced Search

Using the five safes to structure economic evaluations of data governance (2024)
Journal Article
Ritchie, F., & Whittard, D. (in press). Using the five safes to structure economic evaluations of data governance. Data & Policy,

As the world has become more digitally-dependent, questions of data governance such as ethics, institutional arrangements and statistical protection measures have increased in significance. Understanding the economic contribution of investments in da... Read More about Using the five safes to structure economic evaluations of data governance.

The inadvertently revealing statistic: A systemic gap in statistical training? (2024)
Journal Article
Derrick, B., Green, E., Ritchie, F., Smith, J., & White, P. (2024). The inadvertently revealing statistic: A systemic gap in statistical training?. Significance, 21(1), 24-27. https://doi.org/10.1093/jrssig/qmae009

While concerns around data privacy are well-known, there's a lack of awareness and training when it comes to the confidentiality risk of published statistics, argue Ben Derrick, Elizabeth Green, Felix Ritchie, Jim Smith, Paul White

Machine learning models in trusted research environments - Understanding operational risks (2023)
Journal Article
Ritchie, F., Tilbrook, A., Cole, C., Jefferson, E., Krueger, S., Mansouri-Benssassi, E., …Smith, J. (2023). Machine learning models in trusted research environments - Understanding operational risks. International Journal of Population Data Science, 8(1), Article 2165. https://doi.org/10.23889/ijpds.v8i1.2165

IntroductionTrusted research environments (TREs) provide secure access to very sensitive data for research. All TREs operate manual checks on outputs to ensure there is no residual disclosure risk. Machine learning (ML) models require very large amou... Read More about Machine learning models in trusted research environments - Understanding operational risks.

The present and future of the Five Safes framework (2023)
Journal Article
Green, E., & Ritchie, F. (2023). The present and future of the Five Safes framework. Journal of Privacy and Confidentiality, 13(2), https://doi.org/10.29012/jpc.831

The Five Safes has become the default framework for confidential data governance across multiple sectors and countries. Since its inception in 2003, the approach has influenced data management in many ways, particularly in the public sector. As it ha... Read More about The present and future of the Five Safes framework.

Using pedagogical and psychological insights to train analysts using confidential data (2023)
Journal Article
Green, E., & Ritchie, F. (2023). Using pedagogical and psychological insights to train analysts using confidential data. Journal of Privacy and Confidentiality, 13(2), https://doi.org/10.29012/jpc.842

With researchers increasingly gaining access to confidentiality data through restricted environments, interest has grown in the training of those researchers to protect confidentiality and to use the secure facility effectively. Researcher training,... Read More about Using pedagogical and psychological insights to train analysts using confidential data.

Research data governance in low-and middle-income countries (2023)
Report
Ferrer Breda, P., Green, E., Kendal, C., & Ritchie, F. (2023). Research data governance in low-and middle-income countries. Bristol: UWE

Research and policy development on the governance of confidential research data is dominated by the work of academics and government agencies based in high-income countries (HICs). This leaves three quarters of the world’s population faced with a cor... Read More about Research data governance in low-and middle-income countries.

Disclosure control issues in complex medical data (2023)
Presentation / Conference
Green, E., Ritchie, F., Smith, J., Western, D., & White, P. (2023, September). Disclosure control issues in complex medical data. Paper presented at UNECE/Eurostat Expert Group on Statisticial Data Confidentiality, Wiesbaden

The covid19 pandemic assisted the acceleration of routine access to medical records for research. In the UK platforms including OpenSafely and NHSDigital, alongside emerging hospital trust based Trusted Research Environments (TREs), demonstrate the u... Read More about Disclosure control issues in complex medical data.

Towards a comprehensive theory and practice of output SDC (2023)
Presentation / Conference
Derrick, B., Green, E., Ritchie, F., & White, P. (2023, September). Towards a comprehensive theory and practice of output SDC. Paper presented at UNECE/Eurostat Expert Group on Statisticial Data Confidentiality, Wiesbaden

In 2000, the statistical disclosure control of outputs (OSDC) was largely limited to models of table protection developed by and intended for national statistical institutes (NSIs), as a particular branch of general SDC theory. However, in this centu... Read More about Towards a comprehensive theory and practice of output SDC.

Research data governance in low- and middle-income countries (2023)
Presentation / Conference
Ferrer Breda, P., Green, E., & Ritchie, F. (2023, September). Research data governance in low- and middle-income countries. Paper presented at UNECE/Eurostat Expert Group on Statisticial Data Confidentiality, Wiesbaden

Research and policy development on the governance of confidential research data is dominated by the work of academics and government agencies based in high-income countries (HICs). This leaves three quarters of the world’s population faced with a cor... Read More about Research data governance in low- and middle-income countries.

Disclosure control of machine learning models from trusted research environments (TRE): New challenges and opportunities (2023)
Journal Article
Mansouri-Benssassi, E., Rogers, S., Reel, S., Malone, M., Smith, J., Ritchie, F., & Jefferson, E. (2023). Disclosure control of machine learning models from trusted research environments (TRE): New challenges and opportunities. Heliyon, 9(4), Article e15143. https://doi.org/10.1016/j.heliyon.2023.e15143

Introduction: Artificial intelligence (AI) applications in healthcare and medicine have increased in recent years. To enable access to personal data, Trusted Research Environments (TREs) (otherwise known as Safe Havens) provide safe and secure enviro... Read More about Disclosure control of machine learning models from trusted research environments (TRE): New challenges and opportunities.

Frameworks, principles, and accreditation: Making data governance work (2022)
Presentation / Conference
Ritchie, F. (2022, November). Frameworks, principles, and accreditation: Making data governance work. Presented at RSS Data Ethics and Governance – origins, progress and priorities, London

Presentation to the Royal Statistical Society Data Ethics Section, covering the origins and development of the Five Safes, the EDRU approach to problems-solving, principles-based regulation, and how these all need to work together to achieve effectiv... Read More about Frameworks, principles, and accreditation: Making data governance work.

10 is the safest number that there's ever been (2022)
Journal Article
Ritchie, F. (2022). 10 is the safest number that there's ever been. Transactions on data privacy, 15(2), 109-140

When checking frequency and magnitude tables for disclosure risk, the cell threshold (the minimum number of observations in each cell) is a crucial parameter. In rules-based environments, this is a hard limit on what can or can't be published. In pri... Read More about 10 is the safest number that there's ever been.

Disclosure risks in odds ratios and logistic regression (2022)
Presentation / Conference
Derrick, B., Green, E., Ritchie, F., & White, P. (2022, April). Disclosure risks in odds ratios and logistic regression. Paper presented at Scottish Economic Society Annual Conference 2022: Special session 'Protecting confidentiality in social science research outputs', Glasgow

When publishing statistics from confidential data, there exists a risk that the statistic might inadvertently reveal confidential information. Statistical disclosure control (SDC) aims to reduce that risk to an acceptable level. Most SDC theory is co... Read More about Disclosure risks in odds ratios and logistic regression.