Professor Jim Smith
On Study Leave in Terms 1, 2 & 3 2015-16
My interests span foundational, methodological and applied Bayesian statistics and decision theory often in high dimensions. I published a book in September 2010 with Cambridge University Press on my particular take on Bayesian Decision Analysis. I am currently holder of an EPSRC award - with researcher Martien Barons and with Liz Dowler and Rosemary Collier to investigate ways groups of experts can ensure the coherence of their judgments when managing food crises. Martine, Manuelle Leonelli and I now have several publications reproting this work, held one workshop with two more planned in 2016 jointly with collaborators across the world and held several decision conferences to inform this challenging inferential problem.
I have spent many years studying the theory of graphical models, and Bayes Nets especially in developing dynamic and causal variants of these. Over the last few years I have also been developing a new graphical tool - more expressive than the discrete Bayes Net - called a Chain Event Graph. I am now currently investigating various dynamic and decision theoretic extensions of this with Ann Nicholson, Peter Thwaites, Bob Cowell Christiane Gorgen and Rodrigo Collazo: see below. A book on these models with the last two authors above which will appear next year with Chapman and Hall. I have also begun a new collaboration with academics at Leicester University to investigate how these methods might be used in development of decision support in self diagnosis of late onset diabetes.
I have recently applying Bayesian selection to various biological models, for example working with a team studying the use of Bayesian partition models for longitudinal circadian gene expression and more recently for dynamic graphical models of fMRI images of the brain. I have a particular current interest in developing causal discovery algorithms over novel classes of dynamic models, some of which are given above.
The links between algebraic geometry and various graphical models have also fascinated me for a long while especially their associated semi-algebraic structures and I have recently made some new contributions to this area. I am now investigating the geometry of probability tree models: see my recent pulications.
I have had a long interest in Bayesian decision making under conflict and have recently developed multiattribute utility models for helping the design of military training real time decision makers in such environments. I continue to study Bayesian models of forensic evidence and have a special current interest in activity level evidence.
I act as a consultant for the university for a number of well-known companies. In particular I have a long standing interest in methods for combining expert judgments and elicitation and currently participate in a COST joint European award "Expert Judgment Network: Bridging the Gap between Scientific Uncertainty and Evidence based decision making". With Simon French I am collaborating with National Grid to systematically study the security of supply of within the UK gas network.
I headed a successful bid as Co-Director of OxWaSP for an exciting new EPSRC funded initiative to train PhD students from Warwick and Oxford to use and develop new methodological and computational statistical techniques to help cope with the massive data sets and models now now needing analysis in industry and society. I am also currently an active participant in Warwick University Bridges Programme linking research in the Social Sciences with the challenges of Big Data.
To check out some examples of my current academic work see my more recent publications given below. For your convenience I have subdivided these into my publications in Statistics, Decision Analysis and OR, AI and Machine Learning and Mathematical Biology, by journal classification.
Contact him at J.Q.Smith@warwick.ac.uk