Many physical processes are difficult or even impossible to study by conventional experimental methods. As computing power has increased, it has become possible to model some of these processes by sophisticated computer code. In such cases, the code can serve as a proxy for the physical process. As in a physical experiment, one can vary the inputs to the code and observe how the process output is affected. Such studies are called computer experiments and are becoming increasingly popular surrogates for, and adjuncts to, physical experiments.
Much of the methodology for designing, modeling, and analyzing computer experiments can be found only in research papers. The goal of this book is to make these methods accessible to a more general audience. To accomplish this, we have tried to keep the mathematics at a level that will be understandable to readers with Masters level training in Statistics. This has been a challenging task. For example, Gaussian process models are a popular way to describe the output of computer experiments, but Gaussian process models are mathematically complex and likely to be unfamiliar to many readers. We provide an introduction to these models and present references for those who wish to study additional mathematical details of such processes. In other chapters, we relegate mathematical details to notes at the chapter end. To make the book more useful for practitioners, we provide software that can be used to fit the models discussed in the book. Instructions for using the software are included in an Appendix. Examples of the use of the software are interspersed throughout the book. As the software is updated, new versions (and an expanded user's manual) will be put on line through the book web site.)
Add your name to our database of users who receive information about PErK updates by sending your name and email address to Brian Williams
Thomas Santner has been a professor of Statistics at The Ohio State University since 1990. At Ohio State, he has served as Department Chair and Director of the department's Statistical Consulting Service. Previously he was a professor in the School of Operations Research and Industrial Engineering at Cornell University and a Fulbright Scholar visiting Ludwig Maximilians Universitat (Munich). He is a fellow of the American Statistical Association and the Institute of Mathematical Statistics. Santner is also co-author (with D. Duffy) of The Statistical Analysis of Discrete Data and (with Robert Bechhofer and Dave Goldsman) of Design and Analysis of Experiments for Statistical Selection, Screening, and Multiple Comparisons. Brian Williams has been a member of the Statistical Sciences Group at Los Alamos National Laboratory since September 2003. Previously he was associate statistician at the RAND Corporation, where his work on this book was conducted. His research interests include experimental design, computer experiments, Bayesian inference, spatial statistics, and statistical computing. He holds the Ph.D. in statistics from The Ohio State University. William I. Notz is a professor in the Department of Statistics at The Ohio State University. At Ohio State, he has served as acting Department Chair, Associate Dean of the College of Mathematical and Physical Sciences, and Director of the department's Statistical Consulting Service. He has also served as Editor of Technometrics and is a fellow of the American Statistical Association.
|
Professor Thomas Santner Department of Statistics Ohio State University 1958 Neil Avenue Columbus, OH 43210-1247 USA Email: tjs@stat.ohio-state.edu |
Dr. Brian Williams Los Alamos National Laboratory P.O. Box 1663, MS F600, D-1 Los Alamos, NM 87545 USA Email: brianw@lanl.gov |
Professor William Notz Department of Statistics Ohio State University 1958 Neil Avenue Columbus, OH 43210-1247 USA Email: win@stat.ohio-state.edu |
Springer-Verlag with home pages in Germany and the USA.