You are here

Applied Linear Models with SAS

Daniel Zelterman
Cambridge University Press
Publication Date: 
Number of Pages: 
[Reviewed by
Ita Cirovic Donev
, on

Applied Linear Models with SAS is an introductory guide to linear models with an emphasis of step-by-step techniques with SAS. The author presents the book as a textbook for a secondary course in basic statistics with only minimal requirements. I feel that the stated prerequisites (basically, pre-calculus) are too minimal. The reader should posses some more statistics background, as the theory is not presented in such depth. SAS knowldge is not a prerequisite as it slowly introduces itself in the text. However, having some backgroung would definitely enable an easier flow of information.

Chapters are built slowly. Each starts with a narrative example and intuitive explanation of what entails in the rest of the chapter. This helps prepare the reader for the subject at hand, and has him searching for the answers as he reads on.

In the first half of the book, the main feeling is that the author tries to lead the reader to the right path. He often advocates the use of common sense, for example by repeadetly telling the reader to print the data and check the input before any further analysis. He stresses how important it is not to trust the computer, i.e., do not take the result for granted. Alas, this is what I see more and more lately, so such repeated advice is probably not bad.

The second part of the book, in my opinion, is a bit rushed. The rest of the models are explained, again, with as much as intuition as possible, but it is missing the meat. It would have been better to stay at the level of the first chapters.

Exercises are plentiful and applied. One should really go through them to get a real grasp of the subject.

Overall, I think this is an excellent source for students and practitioners without much hands-on experience in linear modeling. With the right amount of dedication from the reader, it can provide an excellent picture of linear models in one's mind. On the other hand, without much theoretical expostion, I have a hard time accepting this as a text for a second course in statistics; a student who doesn't have a grasp of the basic theory cannot fully understand and analyse the output that SAS provides.

Ita Cirovic Donev holds a Masters degree in statistics from Rice University. Her main research areas are in mathematical finance; more precisely, statistical methods for credit and market risk. Apart from the academic work she does statistical consulting work for financial institutions in the area of risk management.

1. Introduction; 2. Principles of statistics; 3. Introduction to linear regression; 4. Assessing the regression; 5. Multiple linear regression; 6. Indicators, interactions, and transformations; 7. Nonparametric statistics; 8. Logistic regression; 9. Diagnostics for logistic regression; 10. Poisson regression; 11. Survival analysis; 12. Proportional hazards regression; 13. Review of methods; Appendix: statistical tables.