Statistical Science


General Theory and Methodology

Theme Overview

The research carried out under this theme covers foundational and theoretical aspects of probability and inferential statistics, and generic statistical methodology. Current research interests include:

  • Philosophical foundations of probability and statistics
  • Theory of inference, including Bayesian theory, predictive inference and asymptotic theory
  • Core Bayesian methodology
  • Statistical methodology for causal inference
  • Inference for stochastic models, nonparametric and semiparametric inference
  • Methodology for multivariate data, including cluster analysis, multivariate calibration and classification
  • Machine learning, classification, pattern recognition
  • Decision analysis via operational research and financial methods

Theme members

Christian Hennig (Theme Lead)Classification; cluster analysis; foundations of statistics; model selection; multivariate data analysis; robust statistics
Gianluca Baio*Bayesian analysis; causal inference from observational data; evaluation of interventions
Richard Chandler*Climatology; environmental sciences; estimating functions; hydrology; inference for dependent data
Codina Cotar*Optimal transport; random graphs; reinforced random walks; statistical mechanics
Petros Dellaportas*Bayesian model choice; graphical models; theory of MCMC
Tom FearnBayesian methods; calibration; classification; multivariate analysis; near infrared spectroscopy
Simon HardenFoundations, inference
Giampiero Marra*Penalised likelihood; microeconomics; splines; simultaneous equation systems; social sciences; unobserved confouding
Sofia Olhede*Ecology; medical imaging; oceanography; penalised likelihood
Yvo Pokern*High-dimensional Gaussian Markov random fields; inference for partially observed and hypoelliptic diffusion processes; nonparametric inference for stochastic differential equations; sequential Monte Carlo methods
Matina RassiasStochastic analysis
Afzal Siddiqui*Energy economics; game theory; optimisation; real options
Jinghao Xue*Hybrid discriminative-generative classification; imbalance learning; partially-supervised learning; statistical pattern recognition

Other members: Elinor JonesFranz Király.*

*These theme members are currently accepting applications for PhD supervision

Current and Recent Externally Funded Projects

  • Statistical modelling and estimation for spatiotemporal data with oceanographic applications, €294k, EU FP7 626775, Apr 2014 - Mar 2017, PI: Olhede.
  • Characterizing Interactions Across Large-Scale Point Process Populations, £152k, EPSRC EP/L001519/1, Jul 2013 - Jun 2015, PI: Olhede.
  • A multicriterion approach for cluster validation, £98k, EPSRC EP/K033972/1, Jun 2013 - May 2017, PI: Hennig.
  • Information geometry for Bayesian hierarchical models, £238k, EPSRC EP/K005723/1, Mar 2013 - Mar 2016, PI: Byrne.
  • Probability, Uncertainty and Risk in the Natural Environment, £683k, NERC NE/J017434/1, Aug 2012 - Aug 2016, PI: Chandler.
  • Semiparametric Sample Selection Modelswith Applications in Biostatistics, Economics and Environmetrics, £100k, EPSRC EP/J006742/1, May 2012 - Jun 2013, PI: Marra.
  • High Dimensional Models for Multivariate Time Series Analysis, £990k, EPSRC EP/I005250/1, Oct 2010 - Sep 2015, PI: Olhede.
  • EnRiMa - Engergy and Risk Management in Public Buildings, €3500k, EC FP7 260041, Oct 2010 - Mar 2014, CI: Siddiqui.