Department of Mathematics & Statistics
The University of Melbourne
Peter Hall is a Professor of Statistics at the University of Melbourne (Australia) and UC Davis. He is an world renowned expert in nonparametric statistics. He is an elected fellow of the Australian Academy of Science (AAS), the Institute of Mathematical Statistics (IMS), the American Statistical Association (ASA), and the Royal Society (FRS). Professor Hall has won numerous awards during his career including the Committee of Presidents of Statistical Societies (COPPS) Presidents’ Award in 1989, the Pitman Medal of the Statistical Society of Australia Inc. (SSAI) in 1992, the Hannan Medal of the AAS in 1994, the IMS Wald Lecturer in 2006. He has held (and currently holds) various leadership positions including President of the Bernoulli Society (2001) and President-Elect of the Institute of Mathematical Statistics (2009).
(December 7, 2009)
Contemporary Frontiers in Statistics
The availability of powerful computing equipment has had a dramatic impact on statistical methods and thinking, changing forever the way data are analyzed. New data types, larger quantities of data, and new classes of research problem are all motivating new statistical methods. We shall give examples of each of these issues, and discuss the current and future directions of frontier problems in statistics.
(December 7, 2009)
Modelling the Variability of Rankings
For better or for worse, rankings of institutions, such as universities, schools and hospitals, play an important role today in conveying information about relative performance. They inform policy decisions and budgets, and are often reported in the media. While overall rankings can vary markedly over relatively short time periods, it is not unusual to find that the ranks of a small number of “highly performing” institutions remain fixed, even when the data on which the rankings are based are extensively revised, and even when a large number of new institutions are added to the competition. In this talk we endeavor to model this phenomenon. We interpret as a random variable the value of the attribute on which the ranking should ideally be based, and we interpret data as providing a noisy approximation to this variable. We show that, if the distribution of the true attributes is light-tailed (for example, normal or exponential), then the number of institutions whose ranking is correct, even after recalculation using new data and even after many new institutions are added, is essentially fixed. Cases where the number of reliable rankings increases significantly when new institutions are added are those for which the distribution of the true attributes is relatively heavy-tailed.