Michael Smith joined MBS in 2007, after eight years as an Associate Professor in the Discipline of Econometrics and Business Statistics at the University of Sydney. During that time he also held visiting positions at the University of Munich and The Wharton School at the University of Pennsylvania. Michael's research is evenly balanced between the development of econometric and statistical models and methods, and their application to solve problems arising in business and elsewhere. He is prominent internationally for his work on Bayesian semiparametric modeling and model averaging in cross-sectional, spatial and time series contexts. His work has appeared widely in top journals in econometrics and statistics, including the Journal of Econometrics, Journal of the American Statistical Association, Journal of Business and Economics Statistics, Journal of the Royal Statistical Society B and the Journal of Computational and Graphical Statistics. He has consulted widely in the energy industry, with a focus on the modeling and forecasting of both demand and spot prices within deregulated wholesale electricity markets.
Articles
Bayesian Identification, Selection and Estimation of Functions in High-Dimensional Additive Models (with Anastasios Panagiotelis), Journal of Econometrics (2008)
In this paper we propose an approach to both estimate and select unknown smooth functions...
Bayesian Density Forecasting of Intraday Electricity Prices using Multivariate Skew t Distributions (with Anastasios Panagiotelis), International Journal of Forecasting (2008)
Electricity spot prices exhibit strong time series properties, including substantial periodicity, both inter-day and intraday...
Spatial Bayesian variable selection with application to functional magnetic resonance imaging (with Ludwig Fahrmeir), Journal of the American Statistical Association (2007)
In this paper we propose a procedure to undertake Bayesian variable selection and model averaging...
Estimation of Binary Markov Random Fields using Markov Chain Monte Carlo (with Daniel Smith), Journal of Computational and Graphical Statistics (2006)
This article compares three binary Markov random fields (MRFs) which are popular Bayesian priors for...
Foreign exchange intervention by the Bank of Japan: Bayesian analysis using a bivariate stochastic volatility model (with Andrew Pitts), Econometric Reviews (2006)
A bivariate stochastic volatility model is employed to measure the effect of intervention by the...
Forthcoming and Working Papers
Bayesian Skew Selection for Multivariate Models (with Anastasios Panagiotelis), Forthcoming in Computational Statistics and Data Analysis (2010)
We develop a Bayesian approach for the selection of skew in multivariate skew t distributions...
Modeling Multivariate Distributions Using Copulas: Applications in Marketing (with Peter J. Danaher), Forthcoming in Marketing Science (2009)
In this research we introduce a new class of multivariate probability models to the marketing...