Date of Award:

5-2024

Document Type:

Thesis

Degree Name:

Master of Science (MS)

Department:

Mathematics and Statistics

Committee Chair(s)

Stephen J. Walsh

Committee

Stephen J. Walsh

Committee

Erin Beckman

Committee

KimberLeigh Hadfield

Abstract

The primary objective of this study is to evaluate the efficacy of the coordinate exchange (CEXCH) algorithm in the generation of robust optimal designs. The assessment involves a comparative analysis, wherein designs produced by the Point Exchange (PEXCH) Algorithm are employed as benchmarks for evaluating the efficiency of CEXCH designs. Three modified criteria, selected from the traditional alphabet criteria pool, are utilized to score each algorithm. To enhance the reliability of the comparative analysis, multiple rounds of validation are conducted, focusing on visual assessments, design scores, and criteria efficiencies. The findings from each round of validation contribute to a comprehensive understanding of the effectiveness of the CEXCH algorithm.

Following the investigation into the effectiveness of CEXCH, the subsequent phase involves the implementation of the algorithm in generating screening designs. Screening experiments are used to extract insightful factors from an extensive list of potential variables.

Exploring insights into the generating designs robust to the loss of two observations, show that the application of the CEXCH algorithm, particularly with the integration of robust criteria, yields designs that compare favorably with alternative criteria and algorithms. These findings highlight the importance of considering the CEXCH algorithm during the preparatory stages of experimental design for researchers seeking robust and effective outcomes.

Checksum

f1c13eb35ec78863559452b43be85733

Download

Share

COinS

Copyright for this work is retained by the student. If you have any questions regarding the inclusion of this work in the Digital Commons, please email us at .