|
Dr Julia Brettschneider
* High-dimensional quality assessment and control for free-form objects in 3D printing/additive layer manufacturing * Preprocessing of biological time series invoking a priori known information Dr Barbel Finkenstadt
* Non-stationary spectral analysis of high frequency biomarker data for chronotherapy * Modelling and Inference for gene regulatory networks * Spatio-temporal modelling of gene expression Professor David Firth
* Fast, accurate and reliable calibration of statistical models with massive datasets (uses ideas from differential geometry, numerical analysis and sampling theory) * Approximate conditional inference with large-scale data streams (a blend of statistical theory and computational statistics) * Longitudinal bibliometrics: Statistical modelling of the "careers" of published research articles, based on historical citation data (statistical modelling coupled with large-scale data management and analysis) Professor Simon French
* Meta-Analysis of expert judgement studies in major risk analyses Professor Mark Girolami
* Variance Reduction for Russian Roulette Sampling for large scale streaming data models * Computational scaling of Russian Roulette Sampling to massive scale statistical models (e.g. in geo-physical statistical models) * Statistical characterisation of Deep Learning with application to acoustic based population-density estimation of bat populations across Europe * Big Data meets Big Models - what are the underlying principles of and how does one assimilate high volume data streams into humongous PDE models describing e.g. global monitoring of ozone levels and subsurface fluid flows * Bayesian methods for ultra-high dimensional data Professor Jane Hutton
* Effective models for seizure rates to assess genetic predisposition to response or resistance to pharmacological treatments * Informative unit and item non-response in longitudinal studies Dr Adam Johansen
* Sequential Monte Carlo for Large Models: Divide and Conquer Approaches * Computational Strategies for Spatial Mixture Modelling with Application to Neuroimaging Data Professor Wilfrid Kendall
* X-ray transforms and statistical geometry for additive layer manufacturing Dr Anthony Lee
* Monte Carlo methodology for parallel and distributed systems Dr Jonathan Marchini
* Neuroimaging genetics : Bayesian methods development for genetic association with high dimensional imaging phenotypes * Statistical genetics methodology for large-scale sequencing and genotyping projects Dr Tom Nichols * Neuromaging Genetics (Big Data Squared): Building sensitive models for genetic association with a high dimensional imaging phenotypes * Neuroimaging Meta-Analysis: Joint modelling of massive volume and point-valued imaging datasets Professor Gesine Reinert
* Probabilistic and statistical network comparisons * Analysis of protein-protein interaction networks Professor Gareth Roberts
* Adaptive MCMC for high-dimensional Monte Carlo * Pseudo-marginal MCMC using epsilon strong simulation Dr David Rossell
* Detection of differentially expressed isoforms from RNA-sequencing experiments * Design and analysis of DNA-sequencing experiments to identify Copy Number Variations Professor Jim Smith
* Dynamic graphical models on evolving domains * Tree models for system discovery in high dimensional domains Dr Dario Spano
* Time-dependent cluster and feature models - probabilist and statistical aspects Dr Simon Spencer
* Validation for network inference |
|
|
