I have been Professor of Management (Statistics) at Melbourne Businss School since 2003. My research interests are in the analysis of categorical data, especially in classification methods, which have seen wide application in marketing research, and also in exact statistical methods, an area which has seen a recent resurgence of interest. My papers and articles have appeared in Journal of the American Statistical Association, Journal of the Royal Society, Biometrika, Biometrics, Statistics in Medicine, Technometrics and Strategic Management Journal. I am also the author of a graduate level textbook on categorical data analysis published by Wiley (1999). Prior to joining MBS, I held a number of other senior academic positions at institutions including the Australian Graduate School of Management, the University of Hong Kong, the University of Waterloo and London's Imperial College. I have consulted widely on behalf of the scientific community, as well as for several prominent legal firms. I was managing editor and joint theory and methods editor of the Australian and New Zealand Journal of Statistics from 2001-2005.
Diagnostic testing
Multinomial Logistic Regression: An Application to Estimating Performance of a Multiple Screening Test for Bowel Cancer when Negatives are Unverified. (with Don J. Frommer), JRSSC (2008)
This paper describes a method of estimating the performance of a multiple screening test where...
Exact testing
Computing highly accurate or exact P-values using importance sampling, Computational Statistics and Data Analysis (2012)
Especially for discrete data, standard first order P-values can suffer from poor accuracy, even for...
A numerical investigation of the accuracy of parametric bootstrap for discrete data (2012)
Standard first order tests have size error that decreases as m^{-1/2} where m is a...
A practical ad-hoc adjustment to the Simes P-value (2011)
The Simes P-value is more powerful than Bonferroni but still suffers from some conservatism when...
Computing Highly Accurate or Exact P-values using Importance Sampling (revised) (2010)
Especially for discrete data, standard first order P-values can suffer from poor accuracy, even for...
How close are alternative bootstrap P-values? (2010)
The bootstrap P-value based on a test statistic T is the exact tail probability of...
Exact confidence intervals
Computing Highly Accurate Confidence Limits from Discrete data using Importance Sampling (2011)
For discrete parametric models, approximate confidence limits perform poorly from a strict frequentist perspective. In...
Computing exact 1-sided limits for relative risk (2011)
A simple construction for optimal and exact upper confidence limits subject to an ordering constraint...
Exact Confidence Bounds for the Risk Ratio in 2x2 Tables with Structural Zero (with Max Moldovan), Biometrical Journal (2007)
This paper examines exact one-sided confidence limits for the risk ratio in a 2x2 table...
Exact one-sided confidence limits for the difference between two correlated proportions (with Max V. Moldovan), Statistics in Medicine (2007)
We construct exact and optimal one-sided upper and lower confidence bounds for the difference between...
Unconditional efficient one-sided confidence limits for the odds ratio based on conditional likelihood (with Max Moldovan), Statistics in Medicine (2007)
We compare various one-sided confidence limits for the odds ratio in a 2x2 table. The...
Higher order asymptotics
How close are alternative bootstrap P-values? (2010)
The bootstrap P-value based on a test statistic T is the exact tail probability of...
Bootstrap and second order tests of risk difference, MBS Working paper (2009)
Standard approximate tests of the difference of two probabilities have type 1 error that can...
Estimated P-values in Discrete Models: Asymptotic and non-asymptotic effects, MBS Working Paper (2008)
The exact null distribution of a P-value typically depends on nuisance parameters unspecified under the...
On approximate conditioning and higher order asymptotics for 2x2 tables, MBS Working papers (2008)
For testing canonical parameters in a continuous exponential family, P-values based on higher order asymptotic...
Exact tests of non-inferiority from independent binomial data based on second order test statistics, MBS Working paper (2008)
Recent advances in likelihood asymptotics (Reid, 2003) lead to pivotal quantities that are closer to...
Choice Modelling
The economic value of improved environmental health in Victorian Rivers, Australasian Journal of Environmental Management (2008)
The non market valuation technique known as choice modelling was used to general benefit estimates...