Book contents
- Frontmatter
- Contents
- Preface
- Acknowledgments
- 1 Introduction
- 2 Principles of Statistics
- 3 Introduction to Linear Regression
- 4 Assessing the Regression
- 5 Multiple Linear Regression
- 6 Indicators, Interactions, and Transformations
- 7 Nonparametric Statistics
- 8 Logistic Regression
- 9 Diagnostics for Logistic Regression
- 10 Poisson Regression
- 11 Survival Analysis
- 12 Proportional Hazards Regression
- 13 Review of Methods
- Appendix: Statistical Tables
- References
- Selected Solutions and Hints
- Index
11 - Survival Analysis
Published online by Cambridge University Press: 05 June 2012
- Frontmatter
- Contents
- Preface
- Acknowledgments
- 1 Introduction
- 2 Principles of Statistics
- 3 Introduction to Linear Regression
- 4 Assessing the Regression
- 5 Multiple Linear Regression
- 6 Indicators, Interactions, and Transformations
- 7 Nonparametric Statistics
- 8 Logistic Regression
- 9 Diagnostics for Logistic Regression
- 10 Poisson Regression
- 11 Survival Analysis
- 12 Proportional Hazards Regression
- 13 Review of Methods
- Appendix: Statistical Tables
- References
- Selected Solutions and Hints
- Index
Summary
Survival data, despite its name, is concerned with the time to an event, not just the death of the subject. The event could be a child learning how to tie her shoes, for example, and the survival time would be the age at which she masters this task. Survival data is different from any of the topics we have described so far, because at the time of the analysis not all of the subjects' data has been completely observed for the event of interest. This is called censoring. We describe a number of examples of time to event data and different types of censoring in this chapter. Survival curves graphically depict the time-to-event data for a data sample, much as a histogram does in elementary statistics. There are some simple statistical comparisons we can make of survival curves. In Chapter 12 we describe a regression model that is useful for modeling survival curves with several explanatory variables in a regression setting.
Censoring
Survival analysis is a collection of statistical methods to model the time it takes for an individual to achieve a specified event. The event could be death, as the name implies, or something less dramatic, such as how long it takes to complete a master's degree, or how long it takes a legislature to pass a bill into law. We provide a number of other examples in this section.
The study of survival data stands apart from other statistical topics because of censoring.
- Type
- Chapter
- Information
- Applied Linear Models with SAS , pp. 225 - 236Publisher: Cambridge University PressPrint publication year: 2010