Basic Introduction to Survival Analysis
A beginner-friendly introduction to survival analysis — the branch of statistics that deals with time-to-event data. The course builds intuition first: why ordinary regression and t-tests fail when observations are censored, what the survival and hazard functions actually mean, and how to reason about risk over time. Students then learn the core practical toolkit — Kaplan-Meier estimation, the log-rank test, and the Cox proportional hazards model — before covering model checking, parametric alternatives, and the classic pitfalls (immortal time bias, informative censoring, misread hazard ratios) that trip up newcomers. Every method is demonstrated in both Python (lifelines, scikit-survival) and R (survival, survminer) on classic teaching datasets from medicine, criminology, and customer analytics, so students leave able to run, interpret, and critique a complete survival analysis end to end.
- Level: beginner
- Duration: 6 weeks
- 7 sections
- Price: $20
Topics: survival analysis, time-to-event, censoring, Kaplan-Meier, hazard function, log-rank test, Cox proportional hazards, hazard ratio, Schoenfeld residuals, Weibull model, accelerated failure time, churn analysis, lifelines, survival package
What's inside
- Basic Introduction to Survival Analysis
- Chapter 1: Time-to-Event Data and the Problem of Censoring
- Chapter 2: The Survival and Hazard Functions, and the Kaplan-Meier Estimator
- Chapter 3: Comparing Groups — The Log-Rank Test and Its Limits
- Chapter 4: The Cox Proportional Hazards Model
- Chapter 5: Checking Assumptions and Diagnosing Your Model
- Chapter 6: Parametric Models, Classic Pitfalls, and Survival Analysis in the Wild