Sofia Villar

I am a senior statistician in the clinical trials methodology group. I was previously awarded the first Biometrika post-doctoral research fellowship. The two-year research fellowship programme I proposed was entitled: Bandit models for the optimal design of clinical trials. Before that (from January 2013- October 2014) I was a research associate in the Department of Mathematics and Statistics of Lancaster University, yet working from the MRC Biostatistics Unit, Cambridge, as part of a joint research project on the design of multi-arm multi-stage clinical trials. I did my Ph.D. thesis on designing tractable and nearly optimal solutions to computationally infeasible constrained sequential estimation problems. The problems I studied are commonly known as multi-armed bandit problems and they have become archetypal models to describe the trade-off between exploration and exploitation that characterises any data learning process.

 My current research involves the developing of methodology for clinical trials that incorporates these dynamic optimisation ideas. In particular, my current research interests are focused on developing Bayesian adaptive designs that use forward-looking algorithms to fully exploit learning from multiple treatments simultaneously. I am interested particularly in the use of this approach to the design of clinical trials for rare diseases.

  I am the Senior Statistician leading a team of statisticians at Papworth Trials Unit Collaboration http://www.royalpapworth.nhs.uk/research/trials/who-we-are/

 

---

Sofia Villar's personal page

---