Survival analysis is the statistical framework for modeling time-to-event data – where the outcome is not just whether something happens, but when. Unlike standard regression, it forces us to deal rigorously with censoring, time-varying risk, and the structure of hazard functions.
In this course, we build survival analysis from first principles. We begin with the probabilistic foundations – survival functions, hazard rates, and likelihood construction – and move toward the core estimators and regression frameworks that define the field, like the Cox Proportional Hazard model, and the Accelerated Failure Time model.
The emphasis is on derivation and intuition. We derive the key estimators, understand what assumptions they encode, and implement everything manually in R.
This series will be updated. On my TODO list are: Frailty models; Recurrent events; Competing risks and multi-state models; Counting process formulation and martingales; Residuals; Censoring and truncation; Survival Trees/Forests and Neural-Networks; Prediction in Survival Analysis; and more.
Curriculum
- 6 Sections
- 21 Lessons
- Lifetime
- Administration1
- Survival Analysis Intro3
- Non Parametric Estimators2
- Survival Regression Models5
- Parametric Models4
- CoxPH Extensions6
