Extending the Linear Model with R: Generalized Linear, Mixed Effects and Nonparametric Regression Models (Texts in Statistical Science) (Hardcover)

by Julian J. Faraway (Author)
Key Phrases: mgcv package, null deviance, gam package, Estimate Std, African Americans, Multiple R-squared (more...)

Editorial Reviews

Review
…This is a very pleasant book to read. It clearly demonstrates the different methods available and in which situations each one applies. It covers almost all of the standard topics beyond linear models that a graduate student in statistics should know. It also includes discussion of topics such as model diagnostics, rarely addressed in books of this type. The presentation incorporates an abundance of well-chosen examples … In summary, this is book is highly recommended…
-Biometrics, December 2006

Product Description
Linear models are central to the practice of statistics and form the foundation of a vast range of statistical methodologies. Julian J. Faraway's critically acclaimed Linear Models with R examined regression and analysis of variance, demonstrated the different methods available, and showed in which situations each one applies. Following in those footsteps, Extending the Linear Model with R surveys the techniques that grow from the regression model, presenting three extensions to that framework: generalized linear models (GLMs), mixed effect models, and nonparametric regression models. The author's treatment is thoroughly modern and covers topics that include GLM diagnostics, generalized linear mixed models, trees, and even the use of neural networks in statistics. To demonstrate the interplay of theory and practice, throughout the book the author weaves the use of the R software environment to analyze the data of real examples, providing all of the R commands necessary to reproduce the analyses. A supporting Web site at www.stat.lsa.umich.edu/~faraway/ELM holds all of the data described in the book. Statisticians need to be familiar with a broad range of ideas and techniques. This book provides a well-stocked toolbox of methodologies, and with its unique presentation of these very modern statistical techniques, holds the potential to break new ground in the way graduate-level courses in this area are taught.

Product Details

• Hardcover: 312 pages
• Publisher: Chapman & Hall/CRC; 1 edition (December 20, 2005)
• Language: English
• ISBN-10: 158488424X
• ISBN-13: 978-1584884248
• Product Dimensions: 9.4 x 6.2 x 0.9 inches
• Shipping Weight: 1.2 pounds (View shipping rates and policies)
• Average Customer Review: 4.0 out of 5 stars See all reviews (1 customer review)
• Amazon.com Sales Rank: #73,345 in Books (See Bestsellers in Books)

  Popular in these categories: (What's this?)

  #4 in	Books > Science > Mathematics > Applied > Linear Programming
  #4 in	Books > Professional & Technical > Professional Science > Mathematics > Applied > Linear Programming

Customer Reviews

Most Helpful Customer Reviews

29 of 29 people found the following review helpful:

4.0 out of 5 stars Flawed but well-explained, July 15, 2007

By	Leicester Dedlock (Ames, IA United States) - See all my reviews

"Extending the Linear Model with R" is a "sequel" of sorts to the impressive "Linear Models with R" also written by Faraway. It assumes a basic knowledge of R (you don't have to be an expert) and a decent understanding of linear models. If you don't have that background, then I would start with the before-mentioned "Linear Models with R". If you read and understood that book, then you should be more than prepared for this one.

This book covers extensions of the linear model including Generalized Linear Models (GLM's), Mixed and Random Effects Models, Nonparametric Regression Models, Additive Models (including GAM's - Generalized Additive Models), and it contains a brief introduction to Regression Trees and Neural Networks. The biggest focus is on Generalized Linear Models. The book is fairly thorough, though not exactly comprehensive, in covering the topic of GLM's and specific commonly used GLM's. The material is very well-explained and easy to follow and they do a good job at integrating code, examples, and graphs in a way that facilitates understanding of both statistical concepts regarding GLM's and also the implementation of these concepts in R. The code is especially useful and it covers most things in R that you will need for this topic, at least those available from CRAN. The book is not very rigorous regarding theory, but that only makes the book easier to read and more practical. However, I do have one complaint regarding this section. The author spends several chapters discussing various commonly used GLM's and THEN finally gets around to defining what a GLM is and covering the basic theory. This seems backwards to me and for this reason I wouldn't read the chapters in order. Also, due to the late coverage of some of the basic theories, we don't get to see the implementation and analysis of certain sub-topics (e.g. leverage and influence) in the early examples.

Mixed and Random Effects models are second in terms of attention received. The organization is better and the explanations and code integration continue to be handled well. Nonparametric Regression and Additive Models only receive one chapter apiece, but both chapters are extremely informative and they are well-explained like the rest of the book. I was especially happy to see the coverage of GAM's (it's very short but useful) since it is a moderately recent topic (1990) and many similar books only make a brief mention of them (hey, GAM's exist) if they are mentioned at all. The chapter on Regression Trees is short, but again they make sure to cover many of the important sub-topics with clarity. The Neural Networks chapter is skimpy and you won't learn much, but it was an unexpected bonus so I can't take off points for that.

Do note that this book takes a regression approach throughout, so look elsewhere for an ANOVA perspective. The book is short with plenty of room left to talk about other topics. Thus, I would have liked to see a second part devoted to an ANOVA approach since I'm the kind of person who hates having to thumb through countless books, but they are open about the book's scope so I can't really complain.

Okay, one more complaint. I would have greatly liked to see an appendix of the R functions used throughout the book with short descriptions and references to where in the book you can find the function being discussed. R Help isn't bad, so it's not a tragic omission, but it still would have been nice.

In summary, this book is extremely useful if you plan on using extensions of linear models with R. Flaws aside, it receives my recommendation.