You are here

Event History and Survival Analysis

Event History and Survival Analysis

Second Edition
Additional resources:

February 2014 | 112 pages | SAGE Publications, Inc

Social scientists are interested in events and their causes. Although event histories are ideal for studying the causes of events, they typically possess two features—censoring and time-varying explanatory variables—that create major problems for standard statistical procedures. Several innovative approaches have been developed to accommodate these two peculiarities of event history data. This volume surveys these methods, concentrating on the approaches that are most useful to the social sciences. In particular, Paul D. Allison focuses on regression methods in which the occurrence of events is dependent on one or more explanatory variables. He gives attention to the statistical models that form the basis of event history analysis, and also to practical concerns such as data management, cost, and useful computer software.

The Second Edition is part of SAGE’s Quantitative Applications in the Social Sciences (QASS) series, which continues to serve countless students, instructors, and researchers in learning the most cutting-edge quantitative techniques.

Visit for more information on the complete QASS "Little Green Book" Series.

Discrete-Time Methods
Parametric Methods for Continuous-Time Data
Cox Regression
Multiple Kinds of Events
Repeated Events


Computer Code
Computer code to accompany this book is available in the link under the "Preview Tab" above.
Key features


  • Provides a more complete treatment of censoring, including a worked example of how to test for sensitivity to informative censoring (in Chapter 2 on Discrete-Time Methods).
  • Gives more attention to accelerated failure time models. There is also more emphasis on interpretation of results and methods for assessing model fit (in Chapter 3 on Parametric Methods for Continuous-Time Data).
  • Includes more detail on the treatment of time-varying explanatory variables, using both the programming statements method and the episode splitting method. There is also more extensive discussion of methods for testing the proportional hazards assumption and methods for handling tied data. Finally, there is a brief section on using the Cox model to generate predictions (in Chapter 4 on Cox Regression).
  • Provides worked examples on testing differences in coefficients across different kinds of events. There is also a new section on cumulative incidence functions, an alternative and increasingly popular approach to competing risks (in Chapter 5 on Multiple Kinds of Events).
  • Describes several new methods that were unavailable when the first edition published, including negative binomial models for event-count data, robust standard errors, and shared frailty (random effects) models.  Methods based on gap times are distinguished from methods based on origin times (in Chapter 6 on Repeated Events).


  • Provides a user-friendly, non-mathematical approach that is accessible, clear, and easy-to-read
  • Emphasizes logistic regression models
Offers social scientists brief yet comprehensive coverage of a key method in quantitative methods

Preview this book

Sample Materials & Chapters

Chapter 1

Program Listings for SAS and STATA

For instructors

Select a Purchasing Option

Electronic version
Prices from
*180 day rental

This title is also available on SAGE Knowledge, the ultimate social sciences online library. If your library doesn’t have access, ask your librarian to start a trial.