Help
R is a programming language that functions as a statistical package because of the many pre-written statistical routines (computer code written to perform a particular task) that are available. It differs from the other packages discussed in this appendix because, rather than being a proprietary product sold or licensed by a corporation, it is a product that is freely available for download. R is sometimes described as “GNU-S” because it is an implementation of the proprietary language S-Plus, which is sold by the Insighful Corporation. It is an extremely powerful system, and new routines are being written and made available on the Internet every day by statisticians and programmers all over the world. Graphics available in R are superior to those produced by almost any other system. Another advantage of using R is that every algorithm in R is available to be read and interpreted by anyone (so you can find out exactly what the computer is doing when it executes a command), in contradistinction to proprietary packages such as SAS and SPSS.
Free is a tough price point to beat, so you may wonder why everyone isn't already using R to do statistical work. The answer is that R is much harder to use than the other packages discussed in this appendix, particularly for someone who doesn't have a lot of aptitude or experience as a programmer. Even the R tutorials and help files may be baffling to the naive user. Using R also requires the programmer to think about what they are doing, to a greater extent than programming in SAS. While this is certainly an educational advantage, people who just want to produce a few simple statistics may not feel that the initial difficulty is worth the investment.
On the other hand, if you start out using R at the same time you learn statistics it may be no more difficult to learn than any other package. There are several GUI implementations available, and as R becomes increasingly common, even more user-friendly adaptations may be developed. A sort of natural experiment is currently taking place as R is increasingly being adopted as a teaching language for beginning statistics, so perhaps in 10 years we will be able to answer this question. One thing is certain: as R becomes more popular and is used more as the first language for introductory statistics classes, more instructional materials appropriate to absolute beginners are being written and distributed. And if you are serious about statistics as a career, you need to become familiar with R because it is the most powerful and flexible language available, and may become the lingua franca of statistical programming in the near future.
To use R, you first need to download it to your computer. The easiest way to do this is to go to the CRAN (Comprehensive R Archive Network) web page (http://cran.r-project.org) and follow the instructions. The next step, unless you are very stout of heart (or already an ace programmer), is to find a good instructional text for R; there are some on the market, and others that may be downloaded from the Internet. You may also want to check out the resources available at http://www.r-project.org/.
R is a command-oriented language: you type commands at a command prompt and the R-interpreter responds interactively, either executing the command or giving you an error message. The commands are quite compact compared to those used in SPSS and SAS, and can appear cryptic to the uninitiated; however, once you learn to use R, you will come to appreciate its efficiency. Even more so than with the other languages discussed in this appendix, the best way to get comfortable with R is to get some basic instructional materials and run through some very simple examples on your computer. The R language is really quite logical, but that logic is easier to recognize through use and practice than by reading someone else's explanation.
Another thing you should know about R is that it is an object-oriented language (as are Java, C++, and Smalltalk, among others, but in distinction to the other packages discussed in this appendix); this basically means that everything you create in R is an object that can be further manipulated by other commands. An object is also a member of a class, meaning that it has certain characteristics and internal organization that allow you to perform operations on it. Again, those are concepts that are easier to understand when you have some experience using an object-oriented language.
An Internet search is one good way to turn up resources, since many instructors using R have made their instructional materials freely available. Instructional books for R include Dalgaard's Introductory Statistics with R (Springer), Maindonald and Brown's Data Analysis and Graphics Using R: An Example-Based Approach (Cambridge), Braun and Murdloch's A First Course in Statistical Programming with R (Cambridge), and Crawley's A Handbook of Statistical Analyses Using R (Chapman & Hall). Instructional materials available from the Internet include Using the R Statistical Computing Environment to Teach Social Statistics Courses by Fox and Anderson (http://www.unt.edu/r...hing-with-R.pdf), Verzani's Using R for Introductory Statistics (http://cran.rproject...ani-SimpleR.pdf), and Baron and Li's Notes on the use of R for psychology experiments and questionnaires (http://www.psych.upe...ych/rpsych.html).
Need to learn statistics as part of your job, or looking for help to pass a statistics course? Statistics in a Nutshell is a clear and concise introduction and reference for anyone with no previous background in the subject. You get a firm grasp of the basics before moving into increasingly advanced material. Each chapter presents you with easy-to-follow descriptions illustrated by graphics, formulas, and plenty of solved examples.
