Methods for Comparing Two Means with Application in Adaptive Clinical Trials

In the design of a clinical trial, the study of the effect of an intervention for a given medical condition is frequently of interest to researcher. Also, in recent years, the use of sequential and adaptive design methods in clinical research and development based on accrued data has become very popular due to its flexibility and efficiency. In this thesis, we derive the Behrens-Fisher distribution, and use the distributional result to examine the effect of an intervention by comparing population means of intervention group and control group. Sample size prediction methods proporting to solve the Behrens-Fisher problem are examined. A new method for solving the Behrens-Fisher problem is proposed. Various sequential and adaptive designs are reviewed.

Name thesis:degree_name

Master of Science in Mathematics (M.S.)

Level thesis:degree_level

Thesis (open access)

Discipline thesis:degree_discipline

Department of Mathematical Sciences

Year dc:date.available

2010

Author dc:creator

• Hu, Fengjiao

Contributors dc:contributor

• Hani Samawi
• Broderick Oluyede

• ETD
• Independent samples
• Normal model
• Paired data
• Random sample
• Sequential methods
• Adaptive methods

Repository record dc:identifier

https://digitalcommons.georgiasouthern.edu/etd/660

OAI identifier oai:identifier

oai:digitalcommons.georgiasouthern.edu:etd-1660