Problems in the Design & Analysis of Computer Experiments

Award Month: 
September-November, 2009

Rapid growth in computer power has made it possible to study complex physical phenomena that might otherwise be too time consuming or expensive to observe. Scientists are able to adjust inputs to computer simulators (or computer codes) in order to help understand their impact on a system. Many such computer simulators require the specification of a large number of input settings and are computationally demanding. This project involves the design and analysis of computer experiments, with emphasis on the study of physics based on engineering simulators. Initial project goals include model calibration and integration of field data with simulator output.

About Project Leader: Dr. Derek Bingham

Dr. Derek Bingham is an Associate Professor and Canada Research Chair in Industrial Statistics in the Department of Statistics and Actuarial Science at Simon Fraser University. He first came to Simon Fraser in 1995 as a PhD student, after earning a B.Sc. in Applied Math from Concordia University, Montreal, Quebec, and an M.Sc. in Statistics from Carleton University, Ottawa, Ontario. After obtaining his Ph.D. in 1999, Dr. Bingham moved to the Department of Statistics at the University of Michigan, Ann Arbor, Michigan, as an Assistant Professor. In 2003, Dr. Bingham joined the Department of Statistics and Actuarial Science at Simon Fraser as the Canada Research Chair in Industrial Statistics. The focus of Dr. Bingham's research has been on the design and analysis of industrial experiments. In Dr. Bingham's words, "New theoretical and algorithmic methodology has been developed for applications with randomization restrictions, robust parameter design and computer experiments. This also includes contributions to Bayesian design and variable selection in industrial applications. My recent work has included experiment design and model selection for investigation of large-scale computer simulators as well as theoretical results for finding multi-stage experiment designs."