|
Activity Number:
|
337
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 11, 2004 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Physical and Engineering Sciences
|
| Abstract - #302224 |
|
Title:
|
Experiment Design in the Presence of Restricted Factor Combinations and Resource Constraints
|
|
Author(s):
|
Joanne R. Wendelberger*+
|
|
Companies:
|
Los Alamos National Laboratory
|
|
Address:
|
Statistical Sciences Group, MS F600, Los Alamos, NM, 87545,
|
|
Keywords:
|
experimental design ; restrictions ; factorial aliasing ; augmented design
|
|
Abstract:
|
In the face of limited resources, statistical design of experiments provides techniques for selecting experimental runs for efficient collection of information. When the number of factors is large, standard design tools such as fractionation and the use of optimal design criteria may be useful. However, practical considerations such as restrictions on certain factor combinations and resource constraints may limit the applicability of standard designs, requiring some ingenuity in the way statistical tools are used to select runs from a set of possible candidates. A materials compatibility study will be used to illustrate the process of identifying a suitable set of runs that makes efficient use of runs in a restricted design space. Careful aliasing of factors in a nonstandard manner leads to a fractional design that allows estimation of the desired effects, while avoiding undesirable factor combinations. The use of optimal design methodology to augment this set of runs with additional candidate runs is also investigated.
|
- 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 2004 program |
