I am a medical statistician with an interest in developing new methodology for design and analysis of clinical trials, meta-analysis and observational studies.

I chair the Unit’s Methodology theme, which comprises four programmes of trial-related research: Design, Conduct, Analysis and Meta-analysis. I lead the Design programme and co-lead the Analysis and Meta-analysis programmes.

I am particularly interested in methods for design of non-inferiority and other trials, including the non-inferiority frontier for non-inferiority trials with uncertain control event rate; the personalised randomised controlled trial (PRACTical) for settings without an accepted standard of care; and the combination of factorial and multi-arm multi-stage trials. Other interests in trials are in causal inference, for example to correct for departures from randomised treatment.

I have worked for many years in missing data, where I have contributed to the widespread use of multiple imputation and am now developing extensions for missing-not-at-random data. I am also particularly interested in meta-analysis and network meta-analysis, where I have developed methods for assessing and testing inconsistency. I co-wrote a tutorial on simulation studies. I have written a range of Stata software.