|
Activity Number:
|
36
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, August 2, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistical Computing
|
| Abstract - #303361 |
|
Title:
|
Uniform Design Over Convex Input Domains with Applications to Computer Experiments
|
|
Author(s):
|
Ying-Chao Hung*+ and Shih-Chung Chuang
|
|
Companies:
|
National Central University and National Central University
|
|
Address:
|
Graduate Institute of Statistics, 300 Jhongda Road, Jhongli, 32049, Taiwan
|
|
Keywords:
|
uniform design ; convex input domains ; computer experiments ; nearly uniform design
|
|
Abstract:
|
The power of uniform design (UD) has received great attention in the area of computer experiments over the last two decades. However, when conducting a typical computer experiment, one finds many non-rectangular types of input domains on which traditional UD methods can not be adequately applied. In this study, we propose a new UD method that is suitable for any convex types of design areas. The proposed method has an important feature that the optimal solution is invariant under coordinate rotations. For practical implementation, we also develop an efficient algorithm to construct a so-called nearly uniform design (NUD) and show that it approximates very well the UD solution. Finally, we illustrate our proposed method on some real examples.
|
