Off-campus Michigan Tech users: To download campus access theses or dissertations, please use the following button to log in with your Michigan Tech ID and password: log in to proxy server

Non-Michigan Tech users: Please talk to your librarian about requesting this thesis or dissertation through interlibrary loan.

Date of Award


Document Type

Campus Access Master's Report

Degree Name

Master of Science in Statistics (MS)

Administrative Home Department

Department of Mathematical Sciences

Advisor 1

Kui Zhang

Committee Member 1

Qiuying Sha

Committee Member 2

Xiao Zhang


Breast cancer is one of most common cancers and leading causes of death for women in United States and in the world. New studies are critically needed for us to better understand, prevent, diagnose, and treat it. In this report, we analyzed a data set consisting of 2,803 breast cancer patients. Our major focus was to validate newly established clinical prognostic staging system from the American Joint Committee on Cancer (AJCC) and compare it with the anatomic staging system from AJCC. Comparing with the anatomic staging system, we found that the clinical prognostic staging system assigned 921 and 660 of patients to higher or lower stage groups. The results from the Kaplan-Meier curves and Cox proportional hazards regression model demonstrated that the clinical prognostic staging system had more power in terms of predicting breast cancer outcomes (Chi-square = 434, p-value < 0.0001) than the anatomic staging system (Chi-square = 384, p-value < 0.0001), especially for patients in clinical prognostic stage group I and III. We performed additional analysis to identify clinicopathologic characteristics that were significantly associated with patients survival, their anatomic stage groups and clinical prognostic stage groups and their power to discriminate the stage groups. Although different sets of clinicopathologic characteristics were found significantly associated with two types of stage groups but the characteristics considered here had high power to discriminate these stage groups. These characteristics may be further studied to improve the cancer staging system.