Table of Contents#### Download Safari Books Online apps: Apple iOS | Android | BlackBerry

## PREFACE TO THE SECOND EDITION

Entire Site

Free Trial

Safari Books Online is a digital library providing on-demand subscription access to thousands of learning resources.

This second edition expands the first edition with the inclusion of new sections, examples, and extensions of statistical methods described in the first edition only in their most elementary forms. New methods sections include analysis of crossover designs (Chapter 9) and multiple comparison methods (Appendix D). Chapters that present repeated measures analysis (Chapter 8), linear regression (Chapter 10), analysis of covariance (Chapter 11), the chi-square test (Chapter 16), and logistic regression (Chapter 20) have been notably expanded, and 50% more examples have been added throughout the book. A new chapter of exercises has also been added to give the reader practice in applying the various methods presented. Also new in this edition is an introduction to α-adjustments for interim analyses (Chapter 2).

Although many of the new features will have wide appeal, some are targeted to the more experienced data analyst. These include discussion of the proportional odds model, the clustered binomial problem, collinearity in multiple regression, the use of time-dependent covariates with Cox regression, and the use of generalized estimating equations in repeated measures analysis. These methods, which are based on more advanced concepts than those found in most of the book, are routinely encountered in data analysis applications of clinical investigations and, as such, fit the description of 'common statistical methods for clinical research'. However, so as not to overwhelm the less experienced reader, these concepts are presented only briefly, usually by example, along with references for further reading.

First and foremost, this is a statistical methods book. It is designed to have particular appeal to those involved in clinical research, biometrics, epidemiology, and other health or medical related research applications. Unlike other books in the SAS Books by Users (BBU) library, SAS is not the primary focus of this book. Rather, SAS is presented as an indispensable tool that greatly simplifies the analyst's task. While consulting for dozens of companies over 25 years of statistical application to clinical investigation, I have never seen a successful clinical program that did not use SAS. Because of its widespread use within the pharmaceutical industry, I include SAS here as the 'tool' of choice to illustrate the statistical methods.

The examples have been updated to Version 8 of SAS, however, the programming statements used have been kept 'portable', meaning that most can be used in earlier versions of SAS as they appear in the examples, unless otherwise noted. This includes the use of portable variable and data set names, despite accommodation for use of long names beginning with Version 8. Because SAS is not the main focus of this book but is key to efficient data analysis, programming details are not included here, but they can be found in numerous references cited throughout the book. Many of these references are other books in the Books by Users program at SAS, which provide the details, including procedure options, use of ODS, and the naming standards that are new in Version 8. For statistical programming, my favorites include Categorical Data Analysis Using the SAS System, Second Edition, by Stokes, Davis, and Koch (2000) and Survival Analysis Using the SAS System, A Practical Guide, by Paul Allison (1995).

I welcome and appreciate reader comments and feedback through the SAS Publications Web site.

Glenn A. Walker July 2002