Statistical Science



Research in Statistical Science is based on a blend of project-based research groups, multidisciplinary collaborations and individual research programmes.

Research Themes

The department's methodological research is organised into six areas:

  • Biostatistics. This theme has a research programme that encompasses both applied health research and the development and evaluation of statistical methods.
  • Computational Statistics. This theme is concerned with advancing the theory, methodology, algorithmic development and application of simulation based approaches, such as Markov Chain Monte Carlo, to statistical inference.
  • Economics, Finance and Business. This theme is concerned with the application of statistical, econometric and machine learning methods to problems arising in economics, finance and business.
  • Environmental StatisticsActivities under this theme include contributions of statistics & data science to applications in any area of environmental science and engineering.
  • General Theory and Methodology. The research carried out under this theme covers foundational and theoretical aspects of probability and inferential statistics, and generic statistical methodology.
  • Multivariate and High Dimensional Data. This theme has a research programme that encompasses both the theoretical and methodological problems encountered when analysing multivariate and high dimensional data.

Much of this work is interdisciplinary and involves collaborations within and outside UCL.

Research Groups

  • Biostatistics Group. The Biostatistics Group (BSG) led by Professor Rumana Omar, conducts both collaborative research with health researchers based in UCL and the associated NHS Trusts and research into statistical methodologies required to address the challenges and needs of biomedical research.
  • Probability at UCL. Research in probability theory begins with fundamental properties of universal stochastic models, and spans applications in life sciences, mathematical physics, finance, insurance and ergodic theory.
  • Methodology for Weather and Climate. This research group focuses on methodology for climate and weather modelling including uncertainty quantification, computer models, data assimilation and machine learning for climate.
  • Statistics for Health Economics Evaluation. The activity of this group revolves around the development and application of Bayesian statistical methodology for health economic evaluation, e.g. cost-effectiveness or cost-utility analysis.
  • High-Dimensional and Functional data. This research group focuses on the interaction of different statistical approaches, and different applied research fields, under a common object of study: data whose dimension is high and even infinite. 
  • Data, Environments, and Learners: Theory and Algorithms. The group's interests revolve around machine learning theory and practice, with a particular interest in learning and certification strategies that are reliable and make efficient use of the available data.