Survival analysis concerns data that can be regarded as
time to an event. The classic example is time to death in medical studies (hence the name), but survival analysis also applies topics such as mechanical failures and customer churn. Obviously survival analysis is an important topic in actuarial fields, but it is also broadly applicable in data science.
Survival Analysis: Techniques for Censored and Truncated Data
John P. Klein And Melvin L. Moeschberger
- In-text exercises
- Answers to odd-numbered exercises
One of the principal challenges of survival analysis is that subjects are typically only observed over a finite window, but outcomes outside of that window are of interest. This book provides detailed coverage of this issue, as well as some advanced survival models. Most of the example applications are biology related, although the techniques can be applied to other fields. One aspect of this book that we really like is that there are solutions to the odd-numbered exercises. Alas, there is little programming guidance. However, packages for survival analysis abound in R, and they exist in Python.