For those who have some theoretical knowledge on statistics and regression techniques, and who want to learn to use R-Project to analyze some data, John Fox wrote just the book.

The introductory chapter shows the most basic aspects of R-Project. Halfway this chapter the reader finds himself analyzing real data using regression techniques. The following chapters introduce the reader to other aspects of the analytical process: reading data into your statistical program, exploring the data and performing some bivariate tests. Then, three full chapters are devoted to regression techniques. While working on practical examples, the reader is introduced to more fundamental aspects of the R-Project software where needed.

The beauty of R is, that anybody can make alterations and additions to it. John Fox did so on many functions, as well as added some functionality that resemble a SPSS-like usage. For instance, recoding in R-Project is normally done using conditionals. This can lead to a somewhat cumbersome process, so Fox wrote his own ‘recode’ function, in which values, or ranges of values, can be specified, as well as output-values. For many people this, and many other functions, will enhance their usage of R-Project. The drawback of this is that the fundamentals of R usage are lost out of sight. But then, the book is called ‘companion to *applied* regression’.

A broad array of analytical techniques is addressed, with a focus on regression. Both linear models as well as generalized models are described. A full chapter is reserved for diagnostics of the model fit. Finally, a chapter is devoted to graphically presenting results and the last chapter gives an introduction to programming in R. Although the book ends there, many other statistical techniques are covered by Fox in web-appendices that are freely available. Among the covered techniques in these appendices are structural equation modeling, multilevel modeling, and several specific types of regression, such as: non-parametric, robust, time-series and nonlinear regression.

This pleasantly written book is excellent for those who want to use R-Project as their main statistical software. Some knowledge on statistics is requires, while all the basics of R-Project are described. For the more advanced techniques, web-appendices were made available. Summarizing, this book is both a very good introduction, as well a reference. As the title says, it is a fine companion.

– – — — —– ——–

**Discuss this article and pose additional questions in the R-Sessions Forum****Find the original article embedded in the manual.**

– – — — —– ——–

R-Sessions is a collection of manual chapters for R-Project, which are maintained on Curving Normality. All posts are linked to the chapters from the R-Project manual on this site. The manual is free to use, for it is paid by the advertisements, but please refer to it in your work inspired by it. Feedback and topic requests are highly appreciated.

——– —– — — – –

This indeed is just the right book if you want to quickly get started. In fact, the writer of this blog once borrowed this book of me, and now, he writes R packages that blow you away (at least me).

Thanks ðŸ˜‰

Or: this once again shows that you should be careful with what you read!