Please read our student and staff community guidance on COVID-19
Skip to main content Skip to navigation

ST912 Statistical Frontiers

Module Leader: Professor Mark Steel

Commitment: 3 hours per week for 9 weeks. This module runs in Term 2.

Summary: Each topic will be presented by a different lecturer, who is an expert in the research area. The lectures are intended to introduce a particular research topic, provide a short overview and stimulate your interest in this particular area. Taken as a whole, the module gives a (necessarily partial and incompete) idea of the breadth of the research interests and expertise within the Department and should thus help you discover the supervisory capacity that is available to you.

Outline for 2019-20:

  • Skorokhod embeddings and where to find them (David Hobson)
  • Inference in absence of likelihood function (Rito Dutta)
  • Bayesian model averaging slides (Mark Steel)
  • Simulation of the extrema of Levy processes (Alex Mijatovic)
  • Methods and algorithms for optimal estimation and inference from statistical models (Ioannis Kosmidis)
  • Bayesian inference and model selection for infectious disease models (Simon Spencer)
  • Hidden Markov Models (Xavier Didelot)
  • New frontiers in Bayesian computation (Gareth Roberts)
  • Approximate Bayesian inference (Christian Robert)
  • A deterministic journey into the unknown (Jeremie Houssineau)
  • Confidential statistical secret sharing (Murray Pollock)
  • Bayesian computation meets applications (Richard Everitt)
  • Adaptive Markov chain Monte Carlo: teach the algorithm how to learn (Krys Latuszynski)
  • Krys Latuszynski - Adaptive Markov chain Monte Carlo: teach the algorithm how to learn
  • Joint decision processes inspired by applications (Julia Brettschneider)
  • Statistics meets mathematical biology: the case of modelling circadian rhythms (Barbel Finkenstadt)
  • Theory of rough paths and applications to statistics (Tessy Papavasiliou)

Assessment: 50% oral examination, 50% essay based coursework

Oral Examination Period: Term 3, Week 3

Deadline: Coursework - term 3, week 5

Feedback: Feedback will be provided within 20 working days.