2005 Cornish Lecture
Date: Wednesday 5th October, 2005
Speaker: Professor Kerrie Mengersen, Queensland University of Technology
Title: Making Decisions based on Data (and other sources of information): A Bayesian Perspective
Abstract:
Almost every decision that we make is based on multiple sources of information. In many fields, such as medicine, natural resources and finance, a critical component of 'evidence-based' decision-making is data, presented through analysis, models, design and so on. However, in practice even these decisions are made by modifying the statistical results in light of the decision-maker’s prior beliefs and other available information. For example, an expert interested in the location of a rare and threatened species might consider a map of predicted presences based on available data, then 'white-out' those areas which in the opinion of the expert the animal would not inhabit. A community group might decide about water management or allocation based on a combination of careful water flow models, statistical water quality analyses and local knowledge. A surgeon may use expert judgement to modify gold-standard risk stratification predictions when deciding about a patient's risk. In most cases this is absolutely what we would want these experts to do, but it is of interest to explore how it might be achieved in a more formal manner; that is, how we might combine this expertise, related results and current data in a single analysis taking into account the relative strengths of the individual sources of evidence.
In this presentation, we explore the use of a Bayesian framework for combining data with priors which can act as vehicles for other information. The ideas will be discussed through a series of case studies in environmental and medical decision-making.
Biography:
Kerrie Mengersen is Professor of Statistics and Acting Director of the Science Research Centre at QUT. She is a supervisor of 10 past and 8 current postgraduate research students. Kerrie's research interests are in the development and application of new statistical methods and related computation. Specific methodological interests are in Bayesian statistics, mixture models, hierarchical modelling and meta-analysis. Her applied interests are in biometrics, biostatistics, environmetrics, genetic statistics and control.
Kerrie has co-authored journal papers and book chapters (45 since 2000) and delivered invited presentations at a wide range of national and international conferences (15 since 2002). Her research is decidedly collaborative, based on international and local networks funded by industry and government sources (CI on 6 ARC grants since 2000).
Kerrie's service to the profession includes membership of six professional societies, executive membership of two of these (SSAI, ISBA), a new role as managing editor of the Australian and New Journal of Statistics, various roles as Program Chair or on the Program Committee of international conferences, a grants reviewer (ARC, NHMRC, Marsden) and a member of the Wesley Hospital Research Institute and the Marsden Foundation. She is also an elected Fellow of the RSS and of the IMS.
Kerrie is an active consultant with experience as a fulltime consultant statistician, Coordinator of the Statistical Consulting unit at QUT and co-Director of Newstat Ltd at The University of Newcastle. She has consulted for 11 major external clients in the past three years and in 2004 she gave five short courses for commercial clients in four states in 2004.