Reader in Statistics, Dr Fabrizio Leisen, from the School of Mathematics, Statistics and Actuarial Science (SMSAS) at the University of Kent, spoke at the Ninth International Workshop on Applied Probability (IWAP) Conference 2018.
Fabrizio spoke during a session on ‘Bayesian Approaches and MCMC’ about his research on ‘Modelling Preference Data with the Wallenius Distribution’.
Abstract
The Wallenius distribution is a generalisation of the Hypergeometric distribution where weights are assigned to balls of different colours. This naturally defines a model for ranking categories which can be used for classification purposes. Since, in general, the resulting likelihood is not analytically available, we adopt an approximate Bayesian computational (ABC) approach for estimating the importance of the categories. We illustrate the performance of the estimation procedure on simulated datasets. Finally, we use the new model for analysing two datasets concerning movies ratings and Italian academic statisticians’ journal preferences. The latter is a novel dataset collected by the authors.
Acknowledgement. This is a work in collaboration with Clara Grazian (University of Oxford) and Brunero Liseo (University of Rome la Sapienza)
Click here for further information about the Conference.
Dr Fabrizio Leisen
Reader in Statistics
Fabrizio is a Reader in Statistics and the Admissions Officer for the MSc in Statistics and MSc in Statistics with Finance degree programmes. He recently secured funding from the Royal Society and the European Commission, being awarded a Marie Curie Career Integration Grant (2014-2018) for the project ‘Flexible Bayesian Non-parametric priors’. His research interests include Bayesian non-parametrics, Markov Chain Monte Carlo (MCMC) methods and Stochastic processes.