There were two plenary talks, by Prof Matt Wand (U Wollongong, Wed 2 Sept) and Prof Vijay Nair (U Michigan, Thurs 3 Sept); see below. Further, there was a plenary session on the future of the Australian & New Zealand Journal of Statistics
(Thurs 3 Sept, 1-2pm), which included an address from the new Managing Editor, Prof Stephen Haslett.
Also, the Statistical Education Talks
were in a single-session slot (i.e. non-parallel), on the afternoon of Thursday 3 Sept, 2-4pm.
Statistics New Zealand
generously sponsored the arrangements for these plenary talks
University of Wollongong
Wednesday 2 September, 9.10-10.10am, CO LT122
Variational approximations in semiparametric regression
Variational approximations are a body of analytic procedures for handling difficult probability calculus problems. They have been used extensively in Statistical Physics and Computer Science. Variational approximations offer an alternative to Markov chain Monte Carlo methods and have the advantage of being faster and not requiring convergence diagnoses, albeit with some loss in accuracy. Despite the growing literature on variational
approximations, they currently have little presence in mainstream Statistics. We describe recent work on the transferral and adaptation of variational approximation methodology to contemporary Statistics settings such as generalised linear mixed models and semiparametric regression. This talk represents joint research with Professor Peter Hall and Dr John T. Ormerod.
University of Michigan
Thursday 3 September, 11.00-12noon, CO LT122
Process monitoring, anomaly detection, and beyond: New directions and applications
There is a huge literature on anomaly detection dealing with statistical process monitoring in manufacturing, engineering process control, and change-point detection. More recent work includes methods for multivariate data, time series, integrating statistical and engineering process control and so on. In this talk, we will provide a brief review of these methods and describe recent developments motivated by new applications. These include various issues in advanced manufacturing, fraud detection in telecommunications and finance, fault detection in sensor networks, monitoring quality of service in communications networks, and biosurveillance.