6:00 p.m. on Tuesday 14th May 2019
Members and guests are invited to mingle over beer, cider, soft drinks and pizza from 5:30 p.m. onwards. Visitors are welcome.
BLAKERS LECTURE THEATRE
SCHOOL OF MATHEMATICS AND STATISTICS
UNIVERSITY OF WESTERN AUSTRALIA
Young Statisticians Meeting
First speaker
Group Based Trajectory Modelling with Monotonicity Constraints
Michael Dymock
Department of Mathematics and Statistics, UWA
ABSTRACT:
The understanding and modelling of developmental trajectories in longitudinal data is of fundamental importance across many areas of research with applications ranging from the health and social sciences to that of marketing. Group based trajectory modelling, an application of finite mixture modelling, is often a first choice in approaching the naturally complex task of modelling these trajectories.
Existing methodology for group based trajectory modelling, implemented through the SAS procedure TRAJ, has been developed over the past two decades with the addition of numerous extensions such as the ability to jointly analyse multiple trajectories as well as the handling of missing data. However, there is no methodology currently in place to impose constraints on the trajectories such as monotonicity. In this work, we develop a new methodology for fitting group based trajectory models with monotonicity constraints. We illustrate the effectiveness of our methodology using both numerical experiments and real world data, with our implementation in the statistical programming language R.
ABOUT THE SPEAKER:
After being awarded the Statistical Society of Australia’s honours scholarship for 2018, Michael went on to achieve first class honours for his research project supervised by Berwin Turlach and Kevin Murray at The University of Western Australia. He has since started working on a PhD at the same university, investigating Bayesian inversion problems. Michael’s research interests lie at the intersection of computational statistics, applied mathematics and dynamical systems. In this talk, he will discuss the progression of his honours research from the early ideas to its current state.
Second speaker
Modelling site-specific Australian daily rainfall with Bayesian mixture models
Connor P. Duffin
Department of Mathematics and Statistics, UWA
ABSTRACT:
Daily rainfall has a large impact on the social behaviour of human beings, and also has wide agricultural, biological, and economic effects. Being able to model location-specific daily rainfall, across the country, is therefore of utmost importance. There are three principal complexities in modelling daily rainfall at a single location: temporal evolution, zero and missing days, and extreme tail behaviour.
This work aims to investigate models that are able to capture these complexities across 151 individual rainfall measurement locations (sites) across Australia. We take a Bayesian approach, and use finite mixture models as a framework to model the discrete and continuous data that comprise these measurements. Temporal evolution is incorporated through the use of a mixture-of-experts structure on the mixture weights. Markov chain Monte Carlo is used to estimate the model, making use of the Pawsey Supercomputing Centre. Results are then analysed through posterior predictive checking, and optimal models are decided on through formal model diagnostics.
ABOUT THE SPEAKER:
Connor completed an Honours degree in Mathematics and Statistics from UWA in 2018, under the supervision of Edward Cripps. His research was in the field of Bayesian computational statistics, on modelling Australian daily rainfall. He has stayed in this field, and is currently pursuing a PhD at UWA, focussing on quantifying and explaining uncertainties in numerical oceanographic models. His current supervisors are Edward Cripps, Thomas Stemler, and Mark Girolami.
For further information please contact the Branch Secretary, Rick Tankard, Murdoch University. He can be reached by email at rick.tankard@murdoch.edu.au or by phone at (08) 9360 2820.
@StatSocAus
