Preface

I'm going to shoot it to you straight: there are a lot of books about data analysis and the R programming language. I'll take it on faith that you already know why it's extremely helpful and fruitful to learn R and data analysis (if not, why are you reading this preface?!) but allow me to make a case for choosing this book to guide you in your journey.

For one, this subject didn't come naturally to me. There are those with an innate talent for grasping the intricacies of statistics the first time it is taught to them; I don't think I'm one of these people. I kept at it because I love science and research and knew that data analysis was necessary, not because it immediately made sense to me. Today, I love the subject in and of itself, rather than instrumentally, but this only came after months of heartache. Eventually, as I consumed resource after resource, the pieces of the puzzle started to come together. After this, I started tutoring all of my friends in the subject—and have seen them trip over the same obstacles that I had to learn to climb. I think that coming from this background gives me a unique perspective on the plight of the statistics student and allows me to reach them in a way that others may not be able to. By the way, don't let the fact that statistics used to baffle me scare you; I have it on fairly good authority that I know what I'm talking about today.

Secondly, this book was born of the frustration that most statistics texts tend to be written in the driest manner possible. In contrast, I adopt a light-hearted buoyant approach—but without becoming agonizingly flippant.

Third, this book includes a lot of material that I wished were covered in more of the resources I used when I was learning about data analysis in R. For example, the entire last unit specifically covers topics that present enormous challenges to R analysts when they first go out to apply their knowledge to imperfect real-world data.

Lastly, I thought long and hard about how to lay out this book and which order of topics was optimal. And when I say long and hard I mean I wrote a library and designed algorithms to do this. The order in which I present the topics in this book was very carefully considered to (a) build on top of each other, (b) follow a reasonable level of difficulty progression allowing for periodic chapters of relatively simpler material (psychologists call this intermittent reinforcement), (c) group highly related topics together, and (d) minimize the number of topics that require knowledge of yet unlearned topics (this is, unfortunately, common in statistics). If you're interested, I detail this procedure in a blog post that you can read at http://bit.ly/teach-stats.

The point is that the book you're holding is a very special one—one that I poured my soul into. Nevertheless, data analysis can be a notoriously difficult subject, and there may be times where nothing seems to make sense. During these times, remember that many others (including myself) have felt stuck, too. Persevere… the reward is great. And remember, if a blockhead like me can do it, you can, too. Go you!