Survival Analysis

From your first censored observation to multi-state, joint and causal survival models: four courses, one path.

Price: $149.99

Courses in this track

1. 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…
2. Introduction to Survival Analysis — Survival analysis is a specialized branch of statistics focused on modeling time-to-event data. Unlike traditional regression methods, it uniquely accounts for censoring — when the event of interest (patient death,…
3. Survival Prediction Modeling: Building and Validating Risk Models — A practical, intermediate course on turning survival models into trustworthy risk predictions. Fitting a Cox model is the easy part; knowing whether its predictions can be believed is the hard part, and it is where…
4. Advanced Survival Analysis: When the Cox Model Isn't Enough — The Cox model is the most useful tool in survival analysis and also the most over-extended. It assumes one event, one transition, one measurement occasion, independent subjects, exact event times, a hazard ratio that…

Survival analysis from your first censored observation to the methods that fix the Cox model when it breaks: four courses, 38 chapters, 219 practice questions and 489 runnable code blocks in R and Python.

Why survival analysis needs its own track

Time-to-event data is everywhere: patients until relapse, customers until churn, loans until default, machines until failure. It is also where ordinary statistics quietly fails. Some subjects haven't had the event yet when the data ends, and an average or a regression that ignores them is biased in a direction you can predict. Fixing that properly takes more than one course. It takes a sequence, and this track is that sequence.

Four courses, one path

1. Foundations. Censoring, the survival and hazard functions, Kaplan-Meier, the log-rank test and the Cox model, built from intuition with no assumed background beyond intro statistics. It ends with the classic pitfalls (immortal-time bias, informative censoring, misread hazard ratios).

2. Core methods. The full toolkit at depth: Nelson-Aalen and hazard smoothing, Cox extensions (stratification, interactions, frailty), diagnostics, parametric and AFT models, competing risks, machine-learning survival models, and three end-to-end projects in healthcare, business and engineering. Courses 1 and 2 overlap on purpose. Course 1 is the gentle on-ramp and course 2 is the full treatment, so if you already know Kaplan-Meier and Cox you can start at step 2.

3. Prediction. Turning a survival model into a risk prediction you can trust: splines, landmarking, penalised Cox, the C-index and time-dependent AUC, calibration and the Brier score, bootstrap optimism correction, and a genuine external validation from the Rotterdam cohort to GBSG. It closes with a complete prognostic model, nomogram and decision curve. This course is taught in R only, because the validation toolchain it relies on exists only in R.

4. Advanced. What to do when the Cox model isn't enough: RMST and non-proportional hazards, flexible parametric and cure models, multi-state and recurrent-event models, frailty, interval censoring and truncation, joint models, Bayesian survival, causal survival analysis, and machine learning evaluated honestly enough to show how often it fails to beat a penalised Cox model.

Code you run, not code you read

Every method is demonstrated in working code: 306 R blocks and 183 Python blocks across the track, using survival, survminer, riskRegression, lifelines and scikit-survival. Where Python has no mature implementation (multi-state, frailty and joint models) the course says so instead of faking it. 109 figures are drawn from the courses' own data, not stock diagrams.

Ask questions, and compare notes

Every course has its own discussion board for enrolled learners. Ask the instructor (replies are highlighted) or talk a problem through with other learners, right next to the chapter you're asking about.

Practical details

• Chapter 1 of every course is free to read before you buy
• Lifetime access: no renewal and no expiry
• Bought separately the four courses cost $269.96; the track is$179.99
• Every course is also available on its own if you only need one stage