Skip to main content

in this section

D. R. Fulkerson Lectures - 2009

Ray Fulkerson made important contributions to the fields of polyhedral combinatorics, network flow theory, matroid theory, graph theory, and large-scale linear programming...


announces the twenty-third
D. R. Fulkerson Lecture Series

Presented by James O. Berger, Ph.D. '74

The Arts and Sciences Professor of Statistics
Department of Statistical Science
Duke University

Read more

"I don't know where I'm gonna go when the volcano blows"

Monday, April 20, 2009 ● 4:30 p.m. ● 101 Phillips Hall

"I don't know where I'm gonna go when the volcano blows," wrote Jimmy Buffet. Great song line, but usually it’s too late to go when the volcano blows; one has to know when to go before the volcano blows.

The problem of risk assessment for rare natural hazards -- such as volcanic pyroclastic flows -- is addressed, and illustrated with the Soufriere Hills Volcano on the island of Montserrat. Assessment is approached through a combination of mathematical computer modeling, statistical modeling of geophysical data, and extreme-event probability computation.

A mathematical computer model of the natural hazard is used to provide the needed extrapolation to unseen parts of the hazard space. Statistical modeling of the available geophysical data is needed to determine the initializing distribution for exercising the computer model. In dealing with rare events, direct simulations involving the computer model are prohibitively expensive, so computation of the risk probabilities requires a combination of adaptive design of computer model approximations (emulators) and rare event simulation.

Working with Inexact Models: The World of Computer Modeling I

Tuesday, April 21, 2009 ● 4:30 p.m. ● 203 Phillips Hall

A major activity in science and engineering is the development of simulation- or math-based computer models of processes. Such models are virtually always incomplete representations of reality. The models will be used, however, so the challenge is to understand how to do so effectively.

Statistical challenges that arise in this area include the need to solve inverse problems and account for the resulting uncertainty, handling uncertainty in inputs, determination of model bias or discrepancy, and development of bias-adjusted predictions. The methodology to be discussed is a mix of Bayesian spatial, hierarchical and nonparametric techniques.

After illustration on a simple pedagogical example, a series of increasingly involved real examples will be discussed. These examples illustrate difficulties such as the need to deal with functional data, the presence of severe confounding, and the surprising phenomenon that full Bayesian analysis is often inferior to a modular, or partial, Bayesian analysis.

Working with Inexact Models: The World of Computer Modeling II

Thursday, April 23, 2009 ● 3:00 p.m. ● 219 Phillips Hall

This will be a continuation of Part I.