The Biometrika Trust offers 2 or 3 year research fellowships, for junior researchers in statistical theory or methodology. It is aimed at those among the most outstanding recent PhD graduates who are capable of self-direction. David Robertson from the MRC Biostatistics Unit was recently awarded a 3 year Biometrika Trust fellowship.
During his fellowship, David plans to develop and implement new methodology that allows error rate control for a variety of modern clinical trial designs which test multiple hypotheses simultaneously. The main areas of focus will include:
- Trials where the multiple hypotheses tested have a natural (and possibly complex) grouping or ordering
- Designs which allow a potentially large number of new treatments to be added throughout the course of the trial
- Multi-arm trials where the probability of patients being randomised to the different treatment arms varies over time, based on the accumulated response data
In the classical framework of drug development, the response to experimental therapies is evaluated one treatment at a time within a homogenous patient group. However, this paradigm is increasingly shifting towards testing multiple related hypotheses simultaneously. Examples include:
- Multi-arm trials, which test multiple treatments in parallel
- Testing targeted therapies across multiple subgroups of patients, which is a key step towards the goal of personalised medicine
- Measuring multiple endpoints to help answer a range of clinical questions
At the same time, there continues to be a strong focus (particularly from a regulatory perspective) on guaranteeing control of a suitable error rate, which is generally formed around the chance of declaring that a treatment has a beneficial effect when in fact no such effect exists.
The new methodology that David will implement during his fellowship will enable more robust inference to be made from such clinical trials, and help ensure that only truly beneficial treatments are recommended to future patients on the basis of trial results.
When and Where
David’s fellowship will begin in December 2018. The BSU will be the host department, which is the natural place to be based, given its long-standing expertise in clinical trial methodology and excellent links with academic and industrial partners in Cambridge and beyond. David’s career development will be supported through mentoring and his ongoing collaboration with Programme Leader, James Wason, as well as a planned collaboration with the statistical methodology group at Novartis.
For more information on Biometrika Trust Fellowships, go to: http://biometrika.wikidot.com/