Survival Analysis- A Self-Learning Text, Third Edition
by David G. Kleinbaum and Mitchel Klein
Springer Publishers New York, Inc.
February 2011
The Authors
Ordering Information

Data Files


This is the third edition of this text on survival analysis, originally published in 1996. As in the first and second editions, each chapter contains a presentation of its topic in “lecture-book” format together with objectives, an outline, key formulae, practice exercises, and a test. The “lecture-book” format has a sequence of illustrations and formulae in the left column of each page and a script in the right column. This format allows you to read the script in conjunction with the illustrations and formulae that high- light the main points, formulae, or examples being presented.

This third edition has expanded the second edition by adding one new chapter, additional sections and clarifications to several chapters,  and a revised computer appendix.

The new chapter is Chapter 10, Design Issues for Randomized Trials, which considers how to compute sample size when designing a randomized trial involving time-to-event data. 

We have expanded Chapter 1 to clarify the distinction between random, independent and non-informative censoring assumptions often made about survival data. We also added a section in Chapter 1 that introduces the Counting Process data layout that is discussed in later chapters (3, 6, and 8).

We added sections in Chapter 2 to describe how to obtain confidence intervals for the Kaplan-Meier (KM) curve and the median survival time obtained from a KM curve.

We have expanded Chapter 3 on the Cox Proportional Hazards (PH) Model by describing the use of age as the time scale instead of time-on-follow-up as the outcome variable. We also added a section that clarifies how to obtain confidence intervals for PH models that contain product terms that reflect effect modification of exposure variables of interest.

We have added sections that describe the derivation of the (partial) likelihood functions for the Stratified Cox (SC) Model in Chapter 5 and the Extended Cox Model in Chapter 6.

We have expanded Chapter 9 on Competing Risks to describe the Fine and Gray model for a sub-distribution hazard that allows for a multivariable analysis involving a Cumulative Incidence Curve (CIC). We also added a numerical example to illustrate the calculation of a Conditional Probability Curve (CPC) defined from a CIC.
The Computer Appendix in the second edition of this text provided step-by-step instructions for using the computer packages STATA, SAS, and SPSS to carry out the survival analyses presented in the main text. We expanded this Appendix to include the free internet-based computer software package call R. We have also updated our description of STATA (version 10.0), SAS (version 9.2) and SPSS (version 16.0). The application of these computer packages to survival data is described in separate self-contained sections of the Computer Appendix, with the analysis of the same datasets illustrated in each section. 

In addition to the above new material, the original nine chapters have been modified slightly to correct for errata in the second edition and to add or modify exercises provided at the end of some chapters.


Authors: David G. Kleinbaum, Professor
Department of Epidemiology
Rollins School of Public Health
1518 Clifton Road NE
Atlanta, Georgia 30322
Phone: 404-727-9667
Fax: 404-727-8737

Mitchel Klein, Research Assistant Professor
Department of Epidemiology
Rollins School of Public Health
1518 Clifton Road NE
Atlanta, Georgia 30322
Phone: 404-727-9667
Fax: 404-727-8737


The Publisher: Springer Publishers New York, Inc.
175 Fifth Avenue
New York, New York 10010

Phone: 1-800-SPRINGER
Fax: 1-201-348-4505




520 pages , 8 1/8 x 9 , 105 illus., hardcover


In the Computer Appendix of the text (pages ), computer programs for carrying out a survival analysis are described. Below are listed the "addicts" and "bladder cancer" datasets that are utilized in the appendix plus other datasets that have been used as examples and exercises throughout the text. The PC user should download any or all of these data sets by right clicking on a given dataset and following your computer's instruction for saving the data-file to your computer.

There are four types of datasets: (1) Stata datasets (with a .dta extension), (2) SAS version 8.2 datasets (with a .sas7bdat extension), (3) SPSS datasets (with a .sav extension), and (4) text datasets (with a .dat extension).


Please direct any additional comments or questions to:

David G. Kleinbaum, Ph.D.
Department of Epidemiology
Rollins School of Public Health
1518 Clifton Road NE
Atlanta, Georgia 30322

Phone: 404-727-9667
Fax: 404-727-8737