PhD projects

I am currently co-supervising Xi Liu on the development of non-parametric quantile models and Paolo Berta on mixture models for health economics.

These are some of the topics on offer for Phd students for 2017:

  1. Calculating and communicating partition uncertainty
    Clustering models are used to identify subsets of the data such that objects in the same group (called a cluster) are more similar, in some sense, to each other than to those in other clusters. Many widely used clustering models are defined by a set of parameters, whose uncertainty can be quantified. However, the output of a clustering model is a partition – the allocation of each object to clusters – and the uncertainty of the partition as a whole is usually overlooked, due to the size and complexity of the partition space. The aims of this PhD project are to develop a framework for calculating partition uncertainty for clustering methods and to develop methods to communicate the partition uncertainty effectively to end users.
  2. Bayesian calibration methods for cardiac electrophysiology models.
    Calibration is the process of using physical data to estimate the tuning parameters in computational models. This PhD project will help to quantify how confident we can be about the outcomes of using a computer model for cardiac electrophysiology models by first quantifying our confidence in the clinical recordings and measuring biological variability. This knowledge is essential if the model is used to guide clinical decision-making to ensure patient safety. This project will be carried out in collaboration with a team at Imperial College London.

Drop me an email if you are interested in any of the projects above. Alternatively, feel free to pitch your own project. Contact me at