Author

Li Yue

Date of Award

2011

Degree Type

Thesis

Degree Name

Master of Science

Program

Epidemiology and Biostatistics

Supervisor

Dr. Guangyong Zou

Second Advisor

Dr. Yun-Hee Choi

Abstract

The performance of a medical diagnostic test yielding quantitative or ordinal measure­ ments is often assessed in terms of its AUC, area under the receiver operating characteristic curve. As new tests constantly being developed, an essential task is to compare multiple AUCs, commonly derived from the same group of subjects. For this purpose, previous research usually uses an omnibus chi-square test that is non-informative and lacks power. In this study, wc propose new methods of constructing simultaneous confidence intervals based on theory of nonparametric [/-statistics. To improve the small sample properties, we adapt the method of variance estimates recovery by obtaining confidence limits for each AUC based on logit and inverse sinh transformation. A large simulation study demon­ strates the good performance of our new method.

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.