Statistical Graphics in SAS: An Introduction to the Graph Template Language and the Statistical Graphics Procedures Reviews

"Dr. Kuhfeld has produced an excellent introduction to the Graph Template Language and the Statistical Graphics Procedures. With many useful code examples for creating custom graph templates, this is a must-have book for those who want to go beyond the default ODS outputs."

Brian Adams
Regulatory Analyst
Dominion Virginia Power

"An Introduction to the Graph Template Language and the Statistical Graphics Procedures, by Warren Kuhfeld, is a book I've been waiting for someone to write, and Kuhfeld does not disappoint.

Statistical graphics in SAS has come a long way in Version 9, with ODS Graphics providing many graphs automatically for statistical procedures, the SG procedures providing direct access to the ODS Graphics engine, and the Graphic Template Language (GTL) providing the means to customize statistical graphs. What was lacking was a book showing users how to apply these methods to their own problems and data.

The book covers all the forms of statistical graphs that can be produced using the SG procedures and the GTL (scatterplots, regression fit plots, boxplots, dot plots, etc.) and a variety of enhancements to make statistical graphs more revealing (smoothed loess curves, data ellipses, etc.). There are many custom features for which I had to write macros back in the days of Versions 6-8, and Kuhfeld illustrates quite nicely how these may be achieved with the SG procedures and the GTL. I particularly liked his strategy of showing how similar effects could be achieved in different ways, illustrating the graphic output side-by-side for easy comparison.

This book will appeal to users who are already somewhat familiar with ODS Graphics as well as to moderately advanced users and developers who need or want to customize graphic output to meet their requirements. It is well organized, containing tables and lists which cross-reference topics in useful ways. The examples illustrate several advanced topics, nicely explained (using macro variables, text labels with Greek letters or special characters, equated axes to preserve plot geometry, etc.). One appendix provides a brief overview of the features of ODS Graphics relevant to this book, while a second presents some helpful techniques for working with the GTL. I heartily recommend this book to those who want to learn how to make the most of these new graphic facilities in SAS."

Michael Friendly
Professor of Psychology
York University