-
PDF
- Split View
-
Views
-
Cite
Cite
A. C. Brooms, The Basics of S-PLUS, 4th edn A. Krause and M. Olson, Journal of the Royal Statistical Society Series A: Statistics in Society, Volume 170, Issue 1, January 2007, Pages 256–257, https://doi.org/10.1111/j.1467-985X.2006.00455_8.x
Close - Share Icon Share
This latest updated edition ties in with the newly available and enhanced features that have been incorporated in the release of S-PLUS version 7.0. (The first two editions of this text were published under the title The Basics of S and S-PLUS; a Web page for each edition can be found at http://www.elmo.ch/doc/splus-book/.)
Ideally suited to those with a comfortable working knowledge of the Windows or UNIX environments, the book intends to raise the reader up to a level of basic competence in the use of S-PLUS. Although there is a natural emphasis on the use of the S language, adequate coverage of the menu-driven commands via the graphical user interface is provided.
The first four chapters describe and discuss the main aspects of the graphical user interface, basic commands for data manipulation (algebraic operations, concatenation and generation of patterned data) and constructs for the storage of data (vectors, arrays, data frames and list objects).
Chapters 5 and 6 go through the graphics facilities for representing data, ranging from the standard plots right through to the ‘Trellis’ graphics utility for depicting data of high dimensionality.
In Chapter 7, methods for exploratory data analysis are discussed. Reviewed are methods for efficient extraction of data summaries, and for the production of plots that help to elucidate the structure of the data, especially in the case where conditioning on a factor is needed. Statistical modelling techniques, including basic multiple linear regression, analysis of variance, generalized linear modelling (with particular focus on logistic regression) and survival data analysis are discussed in Chapter 8.
The functionality of S-PLUS as a good high level programming language (as opposed to just that of a statistical package with a macro writing facility) is introduced and highlighted in Chapters 9–11. Specific techniques that are associated with the object-oriented programming paradigm within the S language are also discussed.
The final few chapters cover additional points on good housekeeping conventions, give advice for deriving the most from the package, flag technicalities that are associated with the internal processing of S-PLUS and give a comparison with its sister free software package R.
It may be that the authors intend that the material does not read too much like a statistics text-book; nevertheless, I would prefer to see the statistical modelling section expanded on a little, along with inclusion of material on basic (autoregressive integrated moving average) time series modelling. However, it could be argued that there are other more appropriate texts that could be consulted for those who want to delve deeper into these areas.
In my view this book is ideal for self-study and is a very appropriate reference text for students who are embarking on a statistics course that is built around S-PLUS, especially where prior experience with the package is either lacking or deficient. It would also be ideal for the graduate researcher who needs to master the package in rapid time (and who is, perhaps, already familiar with a package like MATLAB, in which there are very many parallels).