PHD STUDENTSHIPS IN STATISTICS
1). Strategy Assessment and Tracking: Models for Credit Limit Management
Quantitative Financial Risk Management Centre
Institute for Mathematical Sciences
Imperial College London
Applications are invited for a PhD studentship, funded by Fair, Isaac, to commence as soon as possible. Applicants are expected to have at least a 2(i) degree in a mathematical discipline containing a significant amount of statistics.
A common problem in credit risk management is that of selecting the most appropriate action to take with each account or customer. In particular, this project will focus on credit limit increases and the problems of building effective predictive statistical models, and deciding whether increases should be made, and, if so, how much. The project presents some deep statistical challenges. The student will be working closely with people from the financial services industry, and will require a good working knowledge of that sector.
The project will be supervised by Prof David J. Hand, from whom further information can be obtained ([log in to unmask]). The studentship will run for 3 years. Further information about the department can be found at http://www.ma.imperial.ac.uk.
2). Bayesian Meta Analysis for Microarray Studies
Applications are invited for an EPSRC funded PhD studentship, which is to commence as soon as possible. Applicants are expected to have at least a 2(i) degree in a mathematical discipline containing a significant amount of statistics. The ideal candidate would be familiar with clustering, nonparametric regression or Bayesian inference, and possess good computing skills.
In theory, DNA microarray chip (or ``genechip'') technology for measuring gene regulation offers the potential to discover new taxonomies of disease and lead to a future of improved drug discovery and personalised treatments. In practice, however, the experiments are fairly expensive and their results typically exhibit a low signal to noise ratio. One way to combat this problem is to combine the microarray results with other relevant data sources, such as other microarray experiments, sequence information, textual documents, stimuli similarity, etc, to increase the robustness of any findings. Bayesian modelling provides a coherent, probabilistic framework for combining disparate sources of information. The aim of this project is to develop innovative modelling approaches for combining these different data sources.
The project will be supervised by Dr Nick Heard in the Mathematics Department at Imperial College. Further information can be obtained from Dr Heard by email ([log in to unmask]) The studentship will run for 3.5 years. Eligibility is subject to the College's usual admissions policy. Full funding (fees and maintenance) is available to suitably qualified UK citizens, and suitably qualified EU citizens resident in the UK for the last three years.
For more information regarding graduate studies at Imperial College and to obtain an application form, consult the website http://www.imperial.ac.uk/P1397.htm.
Please post or email your application form, a CV and the names of two referees to Ms Rusudan Svanidze, Department of Mathematics, 180 Queen's Gate, Imperial College London SW7 2RH, ([log in to unmask] <mailto:[log in to unmask]> ). Please state clearly on the application for which position you are applying.
Closing date: Friday 17th November 2006.
Valuing diversity and committed to equality of opportunity
|