Masters Theses

Keywords and Phrases

Supersaturated design; SWEEP operator

Abstract

"Screening experiments are used to determine which factors have a significant effect on a response under the assumption of effect sparsity. These experiments can be crucial in testing potential drugs or improving an industrial process. Supersaturated designs are one answer to this problem, but most existing designs assume the entire experiment will be done at one time. In many situations, the experiment can be done sequentially, using results already obtained to choose the next experimental run. This research evaluates candidate supersaturated designs with eighteen factors and eight initial runs, then eight additional sequentially chosen runs. This type of design was chosen for comparison to some popular existing designs. The initial eight run designs are analyzed with forward regression using the SWEEP operator to find three or fewer significant variables, and then one new run is added to the design using the information found. After eight new runs are added, a fitness value is assigned to the design based on how accurately it identified the true significant parameters. A genetic algorithm hybrid is used to select initial designs utilizing a fitness function based on observed experimental risks"--Abstract, page iii.

Advisor(s)

Drain, David

Committee Member(s)

Gadbury, Gary L.
Adams, C. D. (Craig D.)

Department(s)

Mathematics and Statistics

Degree Name

M.S. in Applied Mathematics

Publisher

University of Missouri--Rolla

Publication Date

Summer 2005

Pagination

ix, 42 pages

Note about bibliography

Includes bibliographical references (pages 39-41).

Rights

© 2005 Angela Marie Jugan, All rights reserved.

Document Type

Thesis - Restricted Access

File Type

text

Language

English

Subject Headings

Experimental design -- Statistical methods
Statistics -- Data processing
Genetic algorithms
Sequential analysis

Thesis Number

T 8815

Print OCLC #

63164208

Link to Catalog Record

Electronic access to the full-text of this document is restricted to Missouri S&T users. Otherwise, request this publication directly from Missouri S&T Library or contact your local library.

http://merlin.lib.umsystem.edu/record=b5478431~S5

Share My Thesis If you are the author of this work and would like to grant permission to make it openly accessible to all, please click the button above.

Share

 
COinS