Event Title

Survival Analysis of Breast Cancer Using Parametric Methods

Streaming Media

Document Type

Event

Description

Survival analysis involves the study of time until an event of interest occurs, or lifetimes. This analysis is used to analyze how long after patients are diagnosed with breast cancer they can live while studying the variables or covariates involved. Hypotheses tests are performed on the different attributes and conclusions are made based on their significance in predicting survival. In this research, I shall perform hypothesis testing to determine differences in survival functions for different groups.

Parametric models are used to represent the relationship between the survival time in months of patients diagnosed with breast cancer and the covariates or the explanatory variables. The parametric models we focus on in this study include Weibull distribution, Exponential distribution, Log-normal, and log- Logistic. These distribution models are thoroughly explained and analyzed for proportional hazards in this study. Accelerated failure time (AFT) models which are parametric regression analysis for log- linear models is discussed and a comparison is made to the parametric proportional hazard function.

Keywords

survival, breast cancer, ethnicity, parametric

Degree

Master of Science (MS)

Department

Mathematics and Statistics

College

Science, Engineering and Technology

First Faculty Advisor's Name

Mezbahur Rahman

First Faculty Advisor's Department

Mathematics and Statistics

First Faculty Advisor's College

Science, Engineering and Technology

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Jepng'etich_Lizzy_Handout.pdf (586 kB)
Presentation Handout

This document is currently not available here.

Share

COinS
 
Apr 17th, 12:00 AM Apr 17th, 12:00 AM

Survival Analysis of Breast Cancer Using Parametric Methods

Survival analysis involves the study of time until an event of interest occurs, or lifetimes. This analysis is used to analyze how long after patients are diagnosed with breast cancer they can live while studying the variables or covariates involved. Hypotheses tests are performed on the different attributes and conclusions are made based on their significance in predicting survival. In this research, I shall perform hypothesis testing to determine differences in survival functions for different groups.

Parametric models are used to represent the relationship between the survival time in months of patients diagnosed with breast cancer and the covariates or the explanatory variables. The parametric models we focus on in this study include Weibull distribution, Exponential distribution, Log-normal, and log- Logistic. These distribution models are thoroughly explained and analyzed for proportional hazards in this study. Accelerated failure time (AFT) models which are parametric regression analysis for log- linear models is discussed and a comparison is made to the parametric proportional hazard function.