Governance models for Non-Specialist Data Science as a catalyst for statistical modernisation

Abstract

National Statistical Offices (NSOs) are increasingly adopting new analytical practices to address growing demands for timely, granular and policy-relevant statistics. Among these, Non-Specialist Data Science (NSDS) has emerged as a strategic approach to expanding analytical capacity by enabling professionals without formal data-science training to conduct advanced analysis within secure institutional environments. This paper presents a comparative study of governance models for NSDS in three NSOs: the UK Office for National Statistics (ONS), France's National Institute of Statistics and Economic Studies (INSEE) in partnership with the Centre d’Accès Sécurisé aux Données (CASD), and Statistics New Zealand (Stats NZ). Drawing on documentary analysis and semi-structured interviews, the study explores how these organisations embed NSDS within the Generic Statistical Business Process Model (GSBPM) and complementary governance mechanisms such as the Five Safes. The findings highlight the importance of secure analytical environments, tiered access regimes, methodological oversight and structured capacity building in supporting expanded analytical participation without undermining statistical quality, confidentiality or institutional credibility. The paper argues that NSDS should be understood primarily as a governance transformation rather than merely a technical innovation, with implications for workforce development, organisational design and international standard-setting in official statistics.