|
Activity Number:
|
280
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Tuesday, July 31, 2007 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
WNAR
|
| Abstract - #309227 |
|
Title:
|
D-Optimal Minimax Response Surface Designs
|
|
Author(s):
|
Julie Zhou*+
|
|
Companies:
|
University of Victoria
|
|
Address:
|
Dept of Mathematics and Statistics, Victoria, BC, V8W 3P4, Canada
|
|
Keywords:
|
optimal designs ; response surface designs ; robust designs ; discrete design space
|
|
Abstract:
|
Quadratic functions can provide good approximation to many response functions in small regions of interest. Thus quadratic models are often assumed and used in response surface designs. One classical design criterion is to minimize the determinant of the variance of the regression estimator, and the designs are called D-optimal designs. The bias of the estimator is ignored. To reflect the nature that quadratic models are only approximately true, we propose a robust design criterion to study response surface designs. Both the variance and the bias are considered in the criterion. In particular, D-optimal minimax designs are investigated and constructed. Examples are given to compare D-optimal minimax designs with classical D-optimal designs.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2007 program |
