Abstract
dc:description.abstract<p>In this work, we take a close look at a general extension to the traditional AB/BA<br />crossover design that is commonly used in clinical trials to determine the effectiveness<br />of new candidate drugs. While the traditional crossover design requires each patient<br />in the study to be measured on both treatment A and treatment B, we consider the<br />possibility of additional measurements being available on each patient. This produces<br />designs such as the AABB/BBAA design which has been used in previous studies.<br />A general test statistic will be derived to test for treatment effects as well as its<br />corresponding power function to aid in sample size determination to aid statistical<br />planning. Lastly, we explore the theoretical power of our testing procedure and<br />compare it to simulated power studies to verify how well sample size determinations<br />will work in practice.</p>
Degree
thesis:*- Name thesis:degree_name
- Master of Science - Mathematical Sciences
- Level thesis:degree_level
- Thesis
- Discipline thesis:degree_discipline
- College of Science and Mathematics
- Year dc:date.available
- 2021
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Nguyen, My T.A
- Contributors dc:contributor
-
- Jacob Turner
- Jeremy Becnel
- Kent Riggs
Subjects
dc:subject × 3Identifiers
dc:identifier.*- Repository record dc:identifier
- https://scholarworks.sfasu.edu/etds/424
- OAI identifier oai:identifier
- oai:scholarworks.sfasu.edu:etds-1455