Books to Learn Statistics using R

What exactly is the book I'm looking for.

What I am looking for is a book that teaches you statistics while using R to give you hands-on experience and thus end up helping you learn R together. I've seen on amazon many books that attempts to do that, but not with R. Examples are Minitab and SAS.

Are the R Book and Statistical Computing an option? - Still not answered.

The R Book and Statistical Computing: An Introduction to Data Analysis using S-Plus seems viable, but a reader opinion here would be helpful and welcome.

How the book relate to statistics courses?

To be even more precise on what I was looking for, consider these two courses learning outcomes on statistics from a math department at the university Im currently a student:

Intermediate Statistics and Probability & Statistics, that is, I'm looking in a book a normal statistics course going to intermediate level but rather than just board and paper having you learning and using R instead. That also means I am looking for a book that assume I want to learn statistics from the beginning.

This book is for researchers too.

I am also a software engineer researcher, but I guess the current situation where you are found with mountains of data and want to learn statistics to go on writing code to automate that is pretty much applicable to many other fields.

That means I'm am not interested on learning every single detail of every single property for every single curve, but am more concerned on making sense of data for my research domain, although I would not mind if the book wanted to go deep on that.

As a final motivation, I find myself reading scientific papers in different sort of communities that claim results based on statistical inference while there is no readable proof if the statistics assumptions/constraints are being violated or not.

A R book that is not much about statistics won't ensure I am not following up on this practice, which is also why I decided looking for a book that is akin to a statistics course using R rather than playing around with a overview book.

Related questions in Cross Validated.

Answers and feedback for this question.


Suggested books were few I already come across but are an example that unfortunately doesn't suits me:

Introductory Statistics with R, Using R for Introductory Statistics, Statistics: An Introduction using R are few of the books that I already looked on amazon but are about an statistics overview or make assumptions that requires previous statistics knowledge. The problem with overview books is mostly about not calling attention to the assumptions, constraints and provide enough explanation to result in make sense of the information.

If you believe there is no book that could fit on this needing as well or think the R book or the Statistical Computing: An Introduction to Data Analysis using S-Plus would fit this, I would also appreciate this type of answer.

@Christopher Aden

Introduction to Probability and Statistics Using R seems to be the closest one but still broad general to what I was looking for.

What I was expecting for is a book such as David S. Moore, The Basics of Statistics because:

  • It covers all statistics subjects.
  • It uses two tools, miniTab and other to give hands-on learning on the just explained method.
  • It very much highlight assumptions and constraints. This is very important for a researcher who has not taken a in depth statistics course and want to use statistics. Hardly overview books will cover them, which is dangerous for researchers.
    • You can see the book table of contents here. Notice how the focus is statistics and the tool usage is to improve understanding and get the student to know how to use tools to do the statistics after learning in an easier way. Its not about the tool, its about statistics!

I want exactly the same thing, but using R.

@Gregory Demin

It uses R as pedagogy examples, assumes you want to learn statistics and best of all, it is open source. Unfortunately, does not cover ANOVA nor ANCOVA, or more advanced subjects.

@Peter Ellis

Good suggestion for a textbook that covers what is wanted in this question.

Books in the asker opinion that answer the question.

@Peter Ellis and @Gregory Demin.

Collection of R Books on Amazon

Amazon discussion about R books for different students background may be found here.

Video Lectures teaching Statistics using R

Google Tech Talks from 2007 that also motivated this question and covers more about Data Mining rather than statistics but using R together here.


6 Answers 6


I think one reason it is so hard to answer this is that R is so powerful and flexible that a real introduction to R programming goes well beyond what is normally needed in an introduction to statistics. The books that teach statistics using MiniTab, JMP or SPSS are doing relatively straightforward things with the software that barely scratch the surface of what R is capable of when it comes to data manipulation, simulations, custom-built functions, etc.

Having said that, I think that Wilcox's Modern Statistics for the Social and Behavioral Sciences: A Practical Introduction (2012) is a brilliant new book. It assumes no statistical knowledge and takes you from scratch right through to a big range of modern robust techniques; and assumes not much more R knowledge than the ability to open it up and load a dataset. It covers many of the classical techniques too including ANOVA (mentioned in the OP).

I would see this book as the equivalent of the books that introduce stats and a stats package like SPSS at the same time. However, it won't teach you to program in R - only how to do modern statistical analysis with it, with an emphasis on robust techniques that address the known problems with classical analysis that are sidelined by most other approaches to teaching statistics.

The three problems with classical methods that this book particularly addresses right from the beginning are sampling from heavy-tailed distributions; skewness; and heteroscedasticity.

Wilcox uses R because "In terms of taking advantage of modern statistical techniques, R clearly dominates. When analyzing data, it is undoubtedly the most important software development during the last quarter of a century. And it is free. Although classic methods have fundamental flaws, it is not suggested that they be completely abandoned... Consequently, illustrations are provided on how to apply standard methods with R. Of particular importance here is that, in addition, illustrations are provided regarding how to apply modern methods using over 900 R functions written for this book."

This book is so excellent that after we bought a copy for work I purchased my own copy at home.

The chapter headings are:

  1. numerical and graphical summaries of data;
  2. probability and related concepts;
  3. sampling distributions and confidence intervals;
  4. hypothesis testing;
  5. regression and correlation;
  6. bootstrap methods;
  7. comparing two independent groups;
  8. comparing two dependent groups;
  9. one-way ANOVA;
  10. two-way and three-way designs;
  11. comparing more than two dependent groups;
  12. multiple comparisons;
  13. some multivariate methods;
  14. robust regression and measures of association;
  15. basic methods for analyzing categorical data;

Further edit - having checked out the David Moore example of what you are looking for, I really think Wilcox's book meets the need.

  • 1
    $\begingroup$ Thank you so much I'm happy to get another reference that is also available as a printable tome. I will edit the main post later to include your reference if no one does that by this time! Really really appreciated. Just to confirm, you mean it teaches you to plot the theory that is mentioned? That is more than fine for me! Please confirm. $\endgroup$ Commented Apr 5, 2012 at 5:38
  • $\begingroup$ I'm not quite sure what you mean by "plot the theory" - but certainly it makes extensive use of plots, and has the R code to do all the theories it covers (both the statistical inference and the plotting). Wilcox also provides his own package of functions or references to others' for the cutting edge robust approaches developed in the past few decades. Each technique comes with examples including code. I've edited the answer to include chapter headings. $\endgroup$ Commented Apr 5, 2012 at 9:14
  • $\begingroup$ Yes you totally got it right! The code pieces that help me do all the theory on R would be very much welcome and necessary in what I am looking into. Thanks for providing the list! I was also in need of a book that would talk about bootstrap. Already ordering this book. Will edit the main post soon. $\endgroup$ Commented Apr 5, 2012 at 15:22
  • $\begingroup$ I'm already browsing this book. +500 on this suggestion, EXACTLY what I was looking for: A fat tome full of information about statistics and the appropriate function to use it on R(which is free and open source yay!). Its very inexpensive for the size of this book and its uniqueness. Don't feel scared for being for behavioral sciences. Im using it despite I am a CS student. I found the behavioral statistics books to be even of more help for me than the statistics one to understand what is going on. Im not saying a pure statistics one is useless, you need one. I used Paul Meyer (1965). $\endgroup$ Commented Apr 10, 2012 at 17:33

May be "Introduction to Statistical Thought"?

  • 1
    $\begingroup$ Great suggestion, I will consider this a valid answer if there is no more answer about this, as this one still doesn't cover more advanced concepts such as ANOVA (or at least that what searching it suggests). Great for being free as well.. $\endgroup$ Commented Apr 1, 2012 at 16:15

@Julie's post of Verzani's book is a real nice choice for someone who has neither R or statistics experience. It's soft enough on both the R and the statistics that it's used by the political science department at UC Davis, and those students have neither programming classes nor higher-level math. His work is available through his CRAN package, simpleR.
Since you come from a Computer Science background, I don't think you need a very gentle introduction to R. I'd assume you have a decent knowledge of data structures, scoping, and why you need a debugger. For a very computing-centric perspective on R (moreso than you might even see in a statistical programming class in an undergrad stat department), check out Norm Matloff's The Art of R Programming. To see if it interests you, Matloff has a very rough draft pre-print version available on his website. If you like his style, I would recommend grabbing the finished copy. He is a CS professor, and he writes the book more to a CS audience than a statistics audience.
G. Jay Kerns (a frequent poster here) also has a book available online called Introduction to Probability and Statistics Using R. I personally feel it does a wonderful service to introducing the guts of R.
I realize your question is targeted to get responses aimed at a CS major, but please also peruse this topic: What book would you recommend for non-statistician scientists?

  • 1
    $\begingroup$ I believe the Introduction to Probability and Statistics Using R is the closest one but still not the one I am looking for. Im editing the question in a second to give a reference of exactly what I am looking for, but unfortunately uses miniTab instead of R. The Art of R Programming seems more concerned with R than the fact of learning of statistics (correct me if I am wrong), and again the previous book concerns me about being rigorous enough on statistics for make assumptions of statistics background, which I, unfortunately lack. I will also summarize the main points. $\endgroup$ Commented Apr 1, 2012 at 5:53
  • $\begingroup$ You are correct about TAoRP--it places more emphasis on programming than learning statistics. I'm a bit confused by your question though. Unless you want to start learning mathematical statistics, you have to make some assumptions and take them on faith--at least briefly. You want a book that introduces statistics, does examples in R, and does not gloss over assumptions? Most intro books will provide some intuition behind modeling assumptions, but may not formalize the logic. You'll need to read a math stats book for that, probably. $\endgroup$ Commented Apr 1, 2012 at 6:06
  • $\begingroup$ Please see the book I just mentioned on my latest edit on the question. It does exactly what I wanted. In fact the question came out of reading pieces of this book. I want the same thing, but with R. I also highlighted in bullets what in the book is so important out of the huge motivation part for those who never came across the book. I hope it is clear now. The table of contents of the book can be seen here as well whfreeman.com/Catalog/product/… $\endgroup$ Commented Apr 1, 2012 at 6:10

I found this book to be of great use, but it does assume some knowledge of basic statistical terms, such as p-value, ANOVA, et cetera.

This book offers a much gentler introduction to statistical concepts themselves...

  • $\begingroup$ +1. Verzani's book is a very gentle introduction, and is also available from his CRAN package. Dalgaard's book is also a nice one, and he certainly speaks as an expert, being no stranger in the R world! $\endgroup$ Commented Apr 1, 2012 at 5:45
  • $\begingroup$ @ChristopherAden -- which book would your recommend for building a solid foundation for thinking about statistics conceptually, without delving (at all, really) into the math itself? $\endgroup$
    – Julie
    Commented Apr 1, 2012 at 6:36
  • $\begingroup$ @Julie, what is your major? One of those days I got a book from 1979 about statistics for sociology students from a social professor. Sometimes they are more helpful, although a professor mentioned on amazon comments that they tend to make more mistakes specially on formulas which is dangerous for professors that are not too much into statistics :( $\endgroup$ Commented Apr 1, 2012 at 7:47
  • $\begingroup$ Julie: That's definitely a question I will be looking into to give better recommendations. I learned from Statistics: The Art and Science of Learning From Data, by Agresti and Franklin. I found it's application-based approach to be great. It does not offer the 50-50 split of statistics-and-R that the OP wanted, so I didn't bother mentioning it. I'm still a rookie to statistics, though, so take my recs with a grain of salt. $\endgroup$ Commented Apr 1, 2012 at 7:53
  • 2
    $\begingroup$ Hi Julie. It would be nice if you can provide a full citation for each book in your answer. :) $\endgroup$
    – cardinal
    Commented Apr 1, 2012 at 16:25

A good book is produced via Adelaide University it is available free online and as a purchase for hardcopy.

Learning Statistics with R

It is very well broken up in its structure and does cover an introduction to R as well as basic introduction to Statistics before moving into more in-depth topics.

There is a very deep list of books on the R website providing it as a reference however currently have not read the titles, will update as I move forward.



Learning Statistics Using R by Randall E. Schumacker is coming out January 2014 from SAGE Publications. It contains all the material in the posting.

  • 4
    $\begingroup$ It's fine for people to let us know about their own work. We deeply appreciate having that kind of first-hand knowledge. It is more than a good idea, though, to acknowledge one's connection with any recommendation: it gives the recommendation more credibility and provides you the credit you deserve, too :-). Perhaps you could take this opportunity, Randy, to amplify your answer, acknowledge your authorship, and say more about why your book would be a great choice for the purposes stated in the question. And welcome to our site! $\endgroup$
    – whuber
    Commented Sep 20, 2013 at 21:24

Not the answer you're looking for? Browse other questions tagged or ask your own question.