Date of Award

12-2020

Degree Type

Creative Project

Degree Name

Master of Science (MS)

Department

Mathematics and Statistics

Committee Chair(s)

Chris Corcoran

Committee

Chris Corcoran

Committee

Daniel Coster

Committee

Yan Sun

Abstract

Conventional asymptotic methods for survival analysis work well when sample sizes are at least moderately sufficient. When dealing with small sample sizes or rare events, the results from these methods have the potential to be inaccurate or misleading. To handle such data, an exact method is proposed and compared against two other methods: 1) the Cox proportional hazards model and 2) stratified logistic regression for discrete survival analysis data.

Share

COinS