The focus of this subject is analysing the time until an event happens, such as the illness or death of a person, or the failure of a business. The issue of censored data is common in such scenarios and how to handle censored data will be discussed throughout this course. The theory, estimation and application of a variety of survival models for censored data are covered, spanning parametric, semi-parametric and non-parametric models. Machine learning methods suitable for censored data are also covered.
|Faculty||Bond Business School|
1. Demonstrate an understanding of censoring and lifetime random variables.
2. Estimate and analyse a variety of survival models, including parametric, non-parametric and proportional hazard models.
3. Demonstrate an understanding of the benefits of machine learning techniques in survival analysis.
4. Estimate and analyse machine learning models in the presence of censored data.
5. Use a statistical package frequently used by practitioners for survival analysis.
There are no co-requisites.
Future offerings not yet planned.