Jim E. Griffin’s Research Page

I am a Professor of Statistical Science in the Department of Statistical Science, University College London. You can find information about my publications from Google Scholar or Research Gate.

Research Interests

• Methodology: Bayesian Nonparametrics, Regression Modelling with High-Dimensional Data, Time Series and Forecasting
• Applications: Economic and Finance Modelling, Anti-doping, Student Performance and Engagement

Research

Bayesian Nonparametrics

• Simulation of non-Gaussian Levy processes - A fast implementation of the Ferguson-Klass algorithm.
• Normalized Latent Measure Factor Models - Factor decompositions of many related densities.
• Survival analysis - Flexible Bayesian nonparametric regression models for survival data.
• Ecology - Polya trees models which can be applied to many typs of ecological data such as capture-recapture, count or ring recovery.

Regression Modelling with High-Dimensional Data

• Efficient Computational Methods for Bayesian Variable Selection - Joint work with Sam Livingstone (UCL) which looks at efficient computational methods for Bayesian variable selection in high-dimension problems and applications in areas such as genomics. Recent work includes samplers for linear models, samplers for generalized linear models and survival analysis, and stucture learning in graphical models.
• Expressing and Visualizing Model Uncertainty in Bayesian Variable Selection - This work develops methods for understanding model uncertainty arising in Bayesian variable selection. Initial work looks using Cartesian credible sets.
• Bayesian Variable Selection in the General Hazards model - Joint work with Javier Rubio (UCL) which develops a g-prior approach for the general hazards model where covariates can enter to the model in two separate parts. Preprint.

Time Series and Forecasting

• Dimension reduction for large vector autoregressions - Recent work includes Bayesian estimation of tensor vector autoregression models, Time-varying Factor Augmented Vector Autoregressions with Grouped Sparse Autoencoders and Time-varying tensor vector autoregression with Yiyong Luo (UCL).
• Dynamic model averaging - An approach for dynamic model averaging with flexible discounting using the loss discounting framework with Dawid Bernaciak (UCL).

Anti-doping

• Performance Passport - This is a joint project with James Hopker (University of Kent) identifying unusual changes in the performance of elite athletes to inform anti-doping. Recent work icludes a Bayesian model for performance evolution with inter and intra season variability and an evaluation of performance as an indicator of doping status.
• An approach to risk scoring with the steroid component of the Athlete Biological Passport

Student Performance and Engagement

• Understanding engagement from virtual learning environment logs - This is a project with Takoua Jendoubi (UCL) and Ioanna Manolopoulou (UCL) A time-varying measure of measuring student engagement.

Statistical Modelling of Environmental DNA (eDNA)

• Single-species eDNA data - Bayesian variable selection in a two-level occupancy model with false positives and false negative with Eleni Matechou (Queen Mary). An Rshiny app is available.
• Multi-species eDNA models - This is a joint project with Eleni Matechou (Queen Mary) and Alex Diana (University of Essex). We have developed multi-species model for biomass changes allowing for errors in eDNA data, a multi-species occupancy model and a model for qPCR data.

Preprints

Some of my current and previous preprints are available from arXiv.org

Code

• Matlab app for the Bayesian nonparametric vector autoregression model in the Journal of Econometrics paper.
• Matlab code for the adaptive Monte Carlo methods in the Biometrika paper.
• Matlab code and R code for finding the Cartesian credible sets in “Expressing and visualizing model uncertainty in Bayesian variable selection using Cartesian credible sets”.
• Code for methods developed in the “Efficient Computational Methods for Bayesian Variable Selection” project are available from Xitong Liang’s GitHub page.
• Code for “A loss discounting framework for model averaging and selection in time series models” is available from Dawid Bernaciak’s GitHub page.
• R code for “Modelling between- and within-season trajectories in elite athletic performance data”.