CHAPTER 21 Summarizing and Graphing Survival Data 301

Chapter 21

Summarizing and

Graphing Survival Data

T

his chapter describes statistical techniques that deal with a special kind of

numerical data called survival data or time-to-event data. These data reflect

the interval from a particular starting point in time, such the date a patient

receives a certain diagnosis or undergoes a certain procedure, to the first or only

occurrence of a particular kind of event that represents an endpoint. Because these

techniques are often applied to situations where the endpoint event is death, we

usually call the use of these techniques survival analysis, even when the endpoint is

something less drastic (or final) than death. Survival data could include time from

resolution of a chronic illness symptom to its relapse, but it can also be a desirable

endpoint, such as time to remission of cancer, or time to recovery from an acute

condition. Throughout this chapter, we use terms and examples that imply that

the endpoint is death, such as saying survival time instead of time to event. However,

everything we say also applies to other kinds of endpoints.

You may wonder why you need a special kind of analysis for survival data in the

first place. Why not just treat survival times as ordinary numerical variables? Why

not summarize them as means, medians, standard deviations, and so on, and

graph them as histograms and box-and-whiskers charts? Why not compare sur-

vival times between groups with t tests and ANOVAs? Why not use ordinary least-

squares regression to explore how various factors influence survival time?

IN THIS CHAPTER»

» ^{Beginning with the basics of}

survival data»

» ^{Generating life tables and trying the}

Kaplan-Meier method»

» ^{Applying some handy guidelines for}

survival analysis»

» ^{Using survival data for even more}

calculations