Chapter 16 Inference for Censored Data and Survival Analysis
The first condition of progress is the removal of censorship.
– George Bernard Shaw
16.1 Introduction
Survival analysis models the survival times of a group of subjects, usually with some kind of medical condition, and generates a survival curve, which shows how many of the subjects are “alive” or survive over time.
What makes survival analysis different from standard regression methodology is the presence of censored observations; in addition, some subjects may leave the study and will be lost to follow-up. Such subjects were known to have survived for some amount of time (up until the time we last saw them), but we do not know how much longer they might ultimately have survived. Several methods have been developed for using this “at least this
long” information to finding unbiased survival curve estimates, the most popular being the nonparametric method of Kaplan and Meier.
An observation is said to be censored if we know only that it is less than (or greater than) a certain known value. For instance, in clinical trials, one could be interested in patients’ survival times. Survival time is defined as the length of time between diagnosis ...
Get Engineering Biostatistics now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
