Survival Analysis Using SAS: A Practical Guide [Paperback]

Paul Allison (Author)

Book Description

Publication Date: November 13, 1995 | ISBN-10: 155544279X | ISBN-13: 978-1555442798 | Edition: 1

Biomedical and social science researchers who want to analyze survival data with SAS will find just what they need with this easy-to-read and comprehensive guide. Written for the reader with a modest statistical background and minimal knowledge of SAS software, this book teaches many aspects of data input and manipulation. Numerous examples of SAS code and output make this an eminently practical resource, ensuring that even the uninitiated becomes a sophisticated user of survival analysis. The main topics presented include censoring, survival curves, Kaplan-Meier estimation, accelerated failure time models, Cox regression models, and discrete-time analysis. Also included are topics not usually covered, such as time-dependent covariates, competing risks, and repeated events.

Editorial Reviews

Review

Written to presume only a basic knowledge of regression analysis and linear models, this is marvelously fluent and presents the survival-analysis material in an enjoyable and readable style. Some of the indigenous topics-such as competing risks, repeated events, multiple events, and event history-receive more emphasis in this book than in most other survival-analysis books. The book incidentally does a nice job of explaining the features in SAS that differentiate SAS survival-analysis capabilities from the capabilities of other (unnamed) survival-analysis software. --Eric R. Ziegel, Technometrics, Book Review Editor

A very informative and practical text for statisticians and applied researchers interested in analyzing time-to-event data. The chapters are concise, well written and packed with useful real life examples. The underlying theory is clearly presented and supplemented with numerous diagrams and tables. Basic survival concepts and methods, such as parametric regression modeling, Kaplan-Meier analysis, and Cox regression are superbly covered. Yet, the text does not shy away from more advanced topics including accelerated failure-time model, time-dependent covariates, and competing risk models. --Jimmy Thomas Efird, Roche Global Development

Allison has put together an excellent resource for survival analysis for the novice, researchers with a limited knowledge of statistics and those with extensive knowledge of statistics. His book contains nine chapters. The first two are introductory information on survival analysis including what survival analysis is, when and why one would use this technique, and approaches to survival analysis including life tables, Kaplan-Meier (KM), exponential regression, and proportional hazard regression. A description of probability functions, including the hazard function are explained in a manner that is easily understood. Chapter 3 explains using the procedure PROC LIFETEST, which produces estimates of survival functions using life tables or KM. Examples and sample data sets are provided for this procedure, and others that follow. Chapter 4 explains the procedure PROC LIFEREG, which produces estimates of parametric regression models with censored survival data using the method of maximum likelihood. Chapter 5 explains use of the procedure PROC PHREG which is proportional hazard modeling or the cox regression model. This procedure is fairly new, and only recently has been included in the core SAS STAT modules. The proportional hazard model has many applications due to the non-parametric nature of the model. Unlike PROC LIFEREG, PHREG does not depend on choosing a particular probability distribution to represent survival times. Allison's description of the model and the syntax for SAS is very easy to follow. Chapter 6 explains concept of competing risks and how to deal with them in the procedures already explained. Chapter 7 explains using PROC LOGISTIC, PROBIT and GENMOD when a survival history is broken down into a set of discrete observations. This chapter provides a quick summary of logistic regression models using SAS, and users with an advance need in this area should use the book Logistic Regression Examples which contains much more detail. Chapter 8 includes advance --Patrick J. Roohan, NYS Department of Health

About the Author

Paul D. Allison is Professor of Sociology at the University of Pennsylvania where he teaches graduate courses in survival analysis and categorical data analysis. Every summer he teaches a five-day workshop on survival analysis that is attended by researchers from around the United States and Canada. Besides his numerous statistical papers, he has also published extensively on the subject of scientists' careers.

Product Details

• Paperback: 304 pages
• Publisher: SAS Publishing; 1 edition (November 13, 1995)
• Language: English
• ISBN-10: 155544279X
• ISBN-13: 978-1555442798
• Product Dimensions: 10.8 x 8.4 x 0.9 inches
• Shipping Weight: 1.6 pounds
• Average Customer Review: 5.0 out of 5 stars  See all reviews (7 customer reviews)
• Amazon Best Sellers Rank: #360,078 in Books (See Top 100 in Books)

More About the Author

Paul D. Allison, Ph.D., is Professor of Sociology at the University of Pennsylvania, and President of Statistical Horizons LLC. You can visit his website at www.StatisticalHorizons.com. After completing doctoral work in sociology at the University of Wisconsin, he did postdoctoral study in statistics at the University of Chicago and the University of Pennsylvania. He has published eight books and more than 60 articles on topics that include linear regression, log-linear analysis, logit analysis, probit analysis, measurement error, inequality measures, missing data, Markov processes, and event history analysis. Much of his earlier research was focused on career patterns of academic scientists. At present, his principal methodological research is focused on the analysis of longitudinal data, especially with determining the causes and consequences of events, and on methods for handling missing data. Each summer he teaches 5-day workshops on survival analysis and logistic regression analysis that draw about 90 doctorate-level researchers from around the U.S. At Penn, he teaches advanced graduate courses on event history analysis, categorical data analysis, and structural equation models with latent variables. A former Guggenheim Fellow, Allison received the 2001 Lazarsfeld Award for distinguished contributions to sociological methodology. In 2010, he was elected as a Fellow of the American Statistical Association.

Customer Reviews

Most Helpful Customer Reviews

21 of 22 people found the following review helpful:

5.0 out of 5 stars Extraordinarily Clear and Useful, February 6, 2000

By A Customer

This review is from: Survival Analysis Using SAS: A Practical Guide (Paperback)

I've used a number of this author's books and they all share in common lucidity, utility, and rigor. This book makes it easy to grasp complex ideas, provides comprehensible examples, gives sample SAS code so that implementing the methods is as straightforward as possible. Plus, it is clear that the author is a subtle and first-rate methodologist, who innovates in this area as well as teaches it.

14 of 14 people found the following review helpful:

5.0 out of 5 stars Learn By Doing, June 13, 2005

By 

Tarek Milleron (Berkeley, CA United States) - See all my reviews
(REAL NAME)   

This review is from: Survival Analysis Using SAS: A Practical Guide (Paperback)

If you have data that fit the general category "time to event," and are not suitably analyzed by repeated measures ANOVA, you are probably looking at doing a survival analysis (also known by several other names). If you are working largely on your own, and you learn best by doing, you cannot--as far as I know--do better than Allison's book. Of course it all but locks you into using SAS for analyses, but his explanations of proportional hazards and other models are the best I've found among a dozen textbooks and stats package manuals (some of which made sense only after reading Allison). What makes this book so good is that it will have you running your analyses in just hours. The examples are superb take-off points. I was not a SAS user before reading the book and therefore took a little extra time to figure out dataset manipulations and such in SAS, but that was minor effort compared to the rewards of having Allison's clearly written book as a guide. The price of this book represents only a fraction of its value.

15 of 18 people found the following review helpful:

5.0 out of 5 stars Best how-to book on survival analysis using SAS. Very useful, June 21, 1999

By A Customer

This review is from: Survival Analysis Using SAS: A Practical Guide (Paperback)

This book is well-written, well-organized, and very practical. I found it invaluable in conducting my research. My only recommendation for the author for his next edition is to include a chapter on dealing with correlated event times, like time-to-promotion and time-to-quiting in his policemen example (pg 249).