-------- Original Message --------
Department of Probability and Statistics University of Sheffield Dorothy Hodgkin Postgraduate Award PhD Studentship Industrial sponsor: Roche Pharmaceuticals Project title: Incorporating prior information into clinical trial planning (see below for description) Supervised by Dr Jeremy Oakley ELIGIBILITY The studentship is only available to student nationals from India, China, Hong Kong, South Africa, Brazil, Russia and the developing world, as defined by the Development Assistance Committee of the OECD. A full list of eligible countries can be found at http://www.oecd.org/dataoecd/35/9/2488552.pdf The eligible countries are all those in Part I of the list, plus Russia and Hong Kong. With the exception of Russia and Hong Kong, none of the countries in Part II of the list are eligible. REQUIREMENTS Candidates should hold a high-grade qualification, at least the equivalent of a UK first class honours degree, from a prestigious academic institution. Candidates should have a strong background in statistics and mathematics. Some knowledge of Bayesian statistics would be desirable, but training will be given as necessary. The project will involve a substantial computing element and experience in a standard statistical computing environment will be an advantage. FEES AND MAINTENANCE GRANT The studentship covers full fees and a maintenance grant of 12,600 pounds per year, for three years. Financial support may also be available in the fourth year, if necessary. APPLICATION PROCEDURE Informal enquiries can be made to Jeremy Oakley, j.oakley@shef.ac.uk, tel: +44 (0) 114 222 3853 (direct line) Applicants can submit a formal application by downloading an application form from http://www.shef.ac.uk/postgraduate/research/apply/index.html Applications will be accepted until the studentship is filled. The studentship will start on 24 September 2007. PROJECT BACKGROUND Both regulators and industry are increasingly aware of falling productivity and the increasing cost of drug development. Expensive and unsuccessful clinical trials can have serious consequences for the time taken for new and better treatments to reach patients. When designing a clinical trial, it is essential to consider the probability of any given trial design producing a positive result. In assessing this probability, sponsors or decision-makers in trial designs will typically only consider the power of the trial, i.e. the conditional probability of a successful trial assuming a specified treatment effect. Since the treatment effect is uncertain, this will not provide a reliable assessment of the probability of a successful outcome and can often give a misleading impression of the likely outcome of the trial. As an alternative to using power, one can consider the unconditional probability of a successful trial outcome that takes into account uncertainty about how effective the treatment actually is. This unconditional probability is known as the assurance. To derive the assurance, the sponsor must consider any relevant prior information about the treatment effect. A prior distribution is constructed to represent this information, and then the unconditional probability of a successful trial be obtained. Typically, the prior distribution is obtained using expert elicitation. However, eliciting prior distributions is rarely a straightforward task. Difficulties in eliciting reliable probability distributions, even in simple cases, have been well documented and the elicitation task can only be made more demanding in trials with more complex outcome measures based on multiple endpoints. Despite the intuitive appeal of assurance, decision-makers will not trust it as an aid to trial design until they have confidence that prior knowledge can be formulated and elicited reliably. In this project we will explore the role of prior elicitation in clinical trial planning, with the aim of designing robust elicitation producers such that assurances can be assessed reliably. Jeremy Oakley Department of Probability and Statistics University of Sheffield The Hicks Building Hounsfield Road Sheffield S3 7RH, UK Phone: +44 114 222 3853 Fax: +44 114 222 3759 http://www.jeremy-oakley.staff.shef.ac.uk/ |