Parametric Mixture Models for Competing Risks Analysis of African-American Breast Cancer Patients

• Activity Number: 315
• Type: Contributed
• Date/Time: Tuesday, August 11, 2015 : 8:30 AM to 10:20 AM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Ram C. Kafle * and Minh Pham and Chris P. Tsokos
• Companies: Sam Houston State University and University of South Florida and University of South Florida
• Keywords: survival ; mixture model ; competing risk ; breast cancer

Abstract

African American breast cancer women experience lowest survival rate compare to other races. The aim of this study is to develop a parametric mixture models for competing risks to study the survival for multiple causes of death and the overall survival of African American breast cancer women. The data set is obtained from the Surveillance Epidemiology and End Results (SEER) of National Cancer Institute. We observe that the survival time in patients in years follow the Weibull distributions for the different causes of death. The factors that may affect the survivability of patients such as age at diagnosis, stage, treatments, histologic tumor grade, behavior of tumor and socioeconomic status are investigated in the study.