|
Activity Number:
|
354
- Experimental Design and Reliability
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 12, 2021 : 10:00 AM to 11:50 AM
|
|
Sponsor:
|
Section on Physical and Engineering Sciences
|
|
Abstract #317868
|
|
|
Title:
|
On the Role of Minimum Variances in Weighted Optimal Designs
|
|
Author(s):
|
Katherine Allen-Moyer* and Jon Stallrich
|
|
Companies:
|
North Carolina State University and North Carolina State
|
|
Keywords:
|
Weighted Optimality;
A-optimality;
Factorial Experiment;
Experimental Design
|
|
Abstract:
|
Weighted optimality criteria allow an experimenter to express hierarchical interest in minimizing variances of estimable functions through a concise weighting system. In this talk, we show how the estimable functions' minimum variances can significantly influence the construction and evaluation of weighted optimal designs. We give a new expression for the weighted A-criterion that involves these minimum variances and show how it helps guide weight selection. We then demonstrate a practical, exploratory approach to weighted design generation and evaluation with factorial experiments.
|
Authors who are presenting talks have a * after their name.
