Data Analysis and Graphics Using R: An Example-based Approach
By addebook • Oct 10th, 2008 • Category: Mathematics •
•
Data Analysis and Graphics Using R: An Example-based Approach (Cambridge Series in Statistical and Probabilistic Mathematics)
Data Analysis and Graphics Using R: An Example-based Approach (Cambridge Series in Statistical and Probabilistic Mathematics)
By John Maindonald, John Braun
Publisher: Cambridge University Press
Number Of Pages: 528
Publication Date: 2006-12-26
ISBN-10 / ASIN: 0521861160
ISBN-13 / EAN: 9780521861168
Binding: Hardcover
Join the revolution ignited by the ground-breaking R system! Starting with an introduction to R, covering standard regression methods, then presenting more advanced topics, this book guides users through the practical and powerful tools that the R system provides. The emphasis is on hands-on analysis, graphical display and interpretation of data. The many worked examples, taken from real-world research, are accompanied by commentary on what is done and why. A website provides computer code and data sets, allowing readers to reproduce all analyses. Updates and solutions to selected exercises are also available. Assuming only basic statistical knowledge, the book is ideal for research scientists, final-year undergraduate or graduate level students of applied statistics, and practising statisticians. It is both for learning and for reference. This revised edition reflects changes in R since 2003 and has new material on survival analysis, random coefficient models, and the handling of high-dimensional data.
Summary: data analysis presented through R
Rating: 4
The authors have written a very good and somewhat unique book on statistical data analysis. The emphasis is on linear models. graphics and diagnostics for identifying violations of modeling assumprions. They build up from the basics starting with simple one variable linear regression and correlation and then moving to multiple regression. Special cases of linear models suchas polynomial regression are presened. They then move on to various generalizations. When the residuals are correlated they consider time series models for the correlation structure of the residuals. Other specialized and important problems such as repeated measures for longitudinal data are covered.
Logistic regression is also introduced and shown to be a member of a larger class of models called generalized linear models which differ from linear models in that the dependent variable is a transformation of the basic dependent variable. The transformation is called the link function. For logistic regression the transformation is called the logit function. Hierarchical (or multi-level)models are also considered.
There is also a chapter on classification and regression trees. The final methods chapter covers multvariate analysis including classifcation, principal components,and propensity scores. These are topics not commonly seen in a first course on regression or data analysis.
What makes the book unique is a thorough introduction to the R programming language and the presntation of every technique with examples in R that both motivate the need for the technique and the details of the implementation in R. There is a lot of R code given and references to a variety of sources for R that can be found on the internet. The book can serve both as an introduction to data analysis and a tutorial on the R programming language. This can be useful as a text for undergraduate and graduate students. It is also an excellent reference for researchers who want to use R and its application to practical problems. The book also has an appendix that shows the relationship between R and S and SPlus, highlighting the differences. The first chapter is a careful introduction to R and the last chapter covers advanced applications in R.
The graphics used throughout the book are excellently presented and there are even a few color graphs. This text has just had a second edition published but my review is based on the 2003 version which is the one I purchased.
Summary: Outstanding
Rating: 5
Very good book for beginners and experienced users. Good presentation, hard cover, wide content…an outstanding book.
Summary: Comprehensive and Comprehensible
Rating: 4
I am using this book as my main resource to learn R from scratch. I had no prior experience with the program. The text is easy to read, and gives you just enough statistical theory to understand the operations without weighing you down with overly-difficult concepts. Many useful ‘references for further reading’ are scattered throughout if you want to know more about any particular method or operation. The book has an accompanying website with examples of code used for all the figures in the book, solutions to selected exercises, and other helpful things. Advanced topics/sections are marked with an asterisk, indicating that a first-time reader may skip over them until a later date. Overall, the book is very explicit about the code used for all the examples, allowing for easy adaptation to the users’ purposes. The exercises at the end of every chapter can be quite challenging, as they often build on concepts presented in the chapter rather than simply reviewing the material. The index is very good (there is one for terms and one for R symbols and functions). Overall, the book is pretty user-friendly for a novice like me, and it covers a broad range of methods of data analysis.
Summary: tailored for a select field of individuals
Rating: 3
The title gives a comprehensive concept of the book content. Data Analysis and Graphics Using R (emphasize ‘R’ !!!). Nothing less and really nothing more, although I would add “Introduction to” at the beginning of the title. This book is intended for someone with little/no background in data analysis or R. This book is meant to fill the gap of researchers who do not know statistics terribly well, but want to do some of their own statistics and only do those stats in R. Others wanting an survey of data analysis topics may also benefit to some degree from this book.
Book Features (may be a pro/con, depending on your perspective):
-starts with a very basic intro to R; absolutely no knowledge is assumed
-basic (not as thorough as I would have liked) intro to data analysis
-basic intro to data analysis (focuses more on implementation in R than theory)
-minimal stats background required (1-2 courses in stats)
Pros:
-good/solid introduction to R linear models and R graphics; if you want to learn about R graphics and also dabble in basic data analysis, this book will likely fit your need
Cons:
-VERY wordy
-takes awhile to get to the point (sometimes starts with a long example — just say what the model is and then give the example, not vice versa which makes it hard to find substance)
-does not typically go into great depth of methods (slightly more than a survey of topics)
-instead of addressing topics in a single location, things seem to be more scattered in the book
-may create an R user who cannot use R’s help adequately; a lot of this book is spoon-feeding commands and focuses less on making the reader figure out how to use R in new realms or really understanding concepts
As mentioned above, this book is VERY wordy. I generally expect books to explain things clearly and concisely. There is nothing concise about this book. Where 1-2 lines are needed, there are 4-5. Also, this book is more breadth than depth. IMO, this book needs a good editor or someone to rewrite things in a concise format, which would allow for a little more complexity as well.
Summary: limited review…
Rating: 4
I found this book to be quite useful for learning R, and for pointing out the pitfalls for new users. It’s especially good to know that there is a website associated with the book that will allow you to download the code used in the book.
There are several good free R resources out there, but in the end I think you get what you pay for. In this case it was nice to have a hard-bound reference with an index and appendix that I could highlight and dog-ear.
I mostly used it as a book for learning R, and not as a stats book. I did notice that there were many good examples of common statistical applications, such as t-stat tests, residual plotting, and the like. In other words, I feel like I got my money’s worth by just using a few chapters and the appendix.
Please Login or Register to read the rest of this content.
Related Posts
