|
Activity Number:
|
273
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Wednesday, August 14, 2002 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistical Computing*
|
| Abstract - #301282 |
|
Title:
|
Computer Experiments and Robust Design
|
|
Author(s):
|
Jeffrey Lehman*+ and Thomas Santner and William Notz
|
|
Affiliation(s):
|
Ohio State University and Ohio State University and Ohio State University
|
|
Address:
|
1958 Neil Ave., Columbus, Ohio, 43220,
|
|
Keywords:
|
Computer experiments ; control variables ; noise variables ; sequential design
|
|
Abstract:
|
Many physical systems can be modeled mathematically so that responses are computable at arbitrary experimental inputs by (complex) computer codes. Running such codes allows us to conduct experiments that are analogs of physical experiments. We are concerned with the design of computer experiments when there are two types of inputs: control variables and environmental variables. Control variables are set by a product designer, and environmental variables are those that are uncontrolled in the field but have some probability distribution. Our interest is in the mean response, over the distribution of the environmental variables, as a function of the control variables. The goal is to find a robust choice of control variables. We review different methods of defining robustness and focus on finding a set of control variables at which the response is insensitive to the value of the environmental variables. Such a choice ensures that the mean response is insensitive to perturbations of the nominal environmental variable distribution. We present a sequential strategy to select the inputs at which to observe the response to determine a robust setting of the control variables.
|
