Patrick Royston, Emeritus Professor of Statistics
Patrick Royston has spent most of his working life applying and researching statistical methods in medicine and allied disciplines.
He joined the MRC Clinical Trials Unit at UCL in 2000, having previously been a professor at the University of London (1993) and in the Department of Statistics and Evaluation, at Imperial College, London, UK. He was a senior statistician at the MRC Clinical Trials Unit at UCL from 2013 until 2023. Patrick was also a Professor of Statistics at UCL.
At the MRC CTU at UCL, Patrick started working on cancer trials and statistical methodology and he later focused on methodology, while still retaining a special interest in cancer trials.
His interests centred on statistical modelling and its medical applications, modelling continuous predictors in observational studies, survival analysis, and methodology of clinical trial design and analysis. He worked on the design and analysis of trials with possible non-proportional hazards of the treatment effect. Patrick also had a strong interest in developing and disseminating software implementation of new research methods using Stata.
He was awarded the 2016 Stata Journal Editors' prize for his contributions. He has co-authored two books; Multivariable model-building. A pragmatic approach to regression analysis based on fractional polynomials for modelling continuous variables (2008) with Willi Sauerbrei of Freiburg University, Germany and Flexible parametric survival analysis using Stata: Beyond the Cox model (2011) with Paul Lambert of Leicester University, UK. He also collaborated with the late Prof Douglas G Altman of Oxford University on a variety of projects over many years.
Patrick now has an emeritus professor role. He will keep contributing to a few lines of work on trial design and analysis with Mahesh Parmar and other MRC CTU at UCL colleagues. He is also continuing his collaboration with Paul Lambert on flexible parametric models in survival analysis.
Royston P, Altman DG (1994) Regression using fractional polynomials of continuous covariates: parsimonious parametric modelling (with Discussion). Applied Statistics 43: 429-467. https://doi.org/10.2307/2986270
Royston P, Parmar MKB, Choodari-Oskooei B, Isham V (2011) Designs for clinical trials with time-to-event outcomes based on stopping guidelines for lack of benefit. Trials 12:81. doi: 10.1186/1745-6215-12-81.
Royston P, Altman DG (2013) External validation of a Cox prognostic model: principles and methods. BMC Medical Research Methodology 13: 33; doi: 0.1186/1471-2288-13-33.
Royston P, Sauerbrei W (2008) Multivariable model-building. A pragmatic approach to regression analysis based on fractional polynomials for modelling continuous variables. Wiley-Blackwell, Chichester.
Royston P, Lambert PC (2011) Flexible parametric survival analysis using Stata: Beyond the Cox model. StataPress, College Station, Texas.
- Applications of flexible parametric models to the design and analysis of phase 3 clinical trials with survival outcomes and possible non-proportional hazards
- Collaborate with Prof Paul Lambert and Dr Mark Rutherford (Leicester University) on a second edition of Royston and Lambert (2011)’s book on flexible parametric survival models.