Revolutions

What is R?

Probably the question I get asked the most about R is, "What is R"? It's can be a hard question to answer, because R is so many things. It's data analysis software. It's an environment for data analysis. It's a language. It's an open-source project. It's a community. The Wikipedia page for R does a great job of describing the details of the features and history of R, but I was looking for something more concise that I could point people to when asked? I wrote up my take on the What is R? at inside-R.org.

Inside-R.org: What is R?

13 videos for learning R

Jeromy Anglim has just posted a nice round-up of instructional videos for learning R. The videos are categorized into four levels:

• What is R?
• Introductory R?
• Intermediate and Advanced Materials on R
• and Related Resources (including a link to written resources for getting started with R).

Check out all the links at Jeromy's post, linked below.

Jeromy Anglim's blog: Videos on Data Analysis with R: Introductory, Intermediate, and Advanced Resources

Smoothing time series with R

Smoothing is a statistical technique that helps you to spot trends in noisy data, and especially to compare trends between two or more fluctuating time series. It's a useful visualization tool that I'm pleased to see cropping up more and more in statistical graphics on the Web -- it's now a staple in econometric charts and is heavily used in polling analysis. For example, here's smoothing used to combine data from various polls over time on Obama's job approval (from pollster.com).

The S language was, to the best of my knowledge, the first software that made statistical smoothing a core part of the graphics system: first with the lowess function and later with other more powerful alternatives. These days in R (S's successor), loess (local polynomrial regression fitting) is the usual go-to alternative for smoothing. With just a couple of lines of code, you can take a noisy time series in R and overlay a smooth trend line to guide the eye. Nathan Yau at FlowingData shows us how to take data like this:

and, with just a few lines of R code and some touching-up in Illustrator, create a chart like this:

FlowingData: How to: make a scatterplot with a smooth fitted line

Video: Hadley Wickham gives a short course on graphics with R

Hadley Wickham (the creator of the popular ggplot2 graphics package for R) has posted video of a 2-hour short course on Visualisation in R at his blip.tv channel. The video is split into four thirty-minute segments:

• Basic Graphics
• Displaying Large Data
• Data manipulation and transformations
• Polishing your plots for publication

The course is peppered with self-guided exercises, for which data, code and the supporting slides are all available. So if you want to be able to create beautiful, informative visualizations of data sets large and small, like this:

then it's well worth two hours of your time to watch these videos. (And don't forget Hadley's book, ggplot2: Elegant Graphics for Data Analysis, for a complete reference.)

Hadley Wickham: data vis mini course

Object types in R: The fundamentals

If you're a self-taught R programmer, you've probably grappled with the different kinds of objects you can use in the language. When should you use a list instead of a vector? What's the difference between a factor and character vector? These questions are easier to answer when you have some of the basics of R's object types down pat, and Chris Bare lays out the fundamentals quite nicely in his blog post The R Type System. An excerpt:

Because the purpose of R is programming with data, it has some fairly sophisticated tools to represent and manipulate data. First off, the basic unit of data in R is the vector. Even a single integer is represented as a vector of length 1. All elements in an atomic vector are of the same type. The sizes of integers and doubles are implementation dependent. Generic vectors, or lists, hold elements of varying types and can be nested to create compound data structures, as in Lisp-like languages.

He goes on from with useful descriptions and examples of matrices, arrays, data frames, factors and more. Well worth checking out if you want to understand how R's object types tick.

Digithead's Lab Notebook: The R type system

Video: What is R?

By popular demand, we've made the video of our 30-minute webcast "The R Project" available on YouTube so that everyone can easily watch it. If you (or a friend!) have ever wondered what this R thing is all about, this is the video for you. Here's the first part:

Because of YouTube restrictions it's split up into four parts, but you can find the other three parts at the link below. There you'll also find also a download link for the slides in PDF format, with lots of useful links to R resources like tutorials, blogs, books and more.

REvolution Computing: The R Project: Data Analysis and Statistical Graphics for the Enterprise

Tips on surviving R

John Mount from Win-Vector LLC gave a very interesting and entertaining talk at this week's Bay Area User Group Meeting, with seven tips for "surviving" R (based on a post on his blog). His recommendations include:

• Keep extensive written notes
• Find a way to search for R answers
• Learn to convert complex objects to canonical forms with unclass()
• Learn how to find and inspect classes and methods for objects
• Learn how to clear pesky attributes from objects
• Swallow your pride (which I interpret as the equivalent to Tim Gunn's "Make it work!")
• and learn and use R's many one-line idioms, rather than reinventing the wheel.

It's always interesting to me how people approach the R language differently, and especially for those coming to R for languages where concepts like classes and attributes can seem a little arcane in R, this is a good guide for escaping some of those early "gotcha" moments. Check out all the details in the post linked below.

Win-Vector Blog: Survive R

Matlab / R Reference

Thanks to the blog Tot Sententiae and reader KM, I just discovered this excellent reference guide to R for Matlab users by University of Maine professor David Hiebeler. For 299 different tasks in areas including mathematical computations, programming constructs, probability distributions and graphics, it gives both the Matlab commands and the equivalent R code. There's also a comprehensive index of each listed Matlab command making it a handy quick reference for translations. (There's an index of R commands too, so I guess it also serves as a guide if you wanted to transition from R to Matlab. But why would you want to do that?) 

David Hiebeler: MATLAB® / R Reference

R Examples for Actuaries

Sometimes I think "Web Archaeology" ought to be a recognized discipline. There are some real treasures to be found in long-abandoned websites, with just a little exploration.

For example, today I stumbled on the website for "R Souls", a user group devoted to the actuarial uses of R at Lloyds of London. Seems like it hasn't been active for a few years. (I resisted the temptation to edit the wiki page to change the name to "Lost R Souls".) Nonetheless, it looks like they had an interesting series of meetings back in 2006 and took good notes. You can still see some useful examples of R for actuarial analysis, including curve-fitting and fitting censored distributions.

One of the group's members, Nigel De Silva, also wrote a useful document: A introduction to R: Examples for Actuaries. The first part of the document is your typical introduction to R syntax and objects (albeit using actuarial data for the examples), but it's the last dozen pages that may be of particular interest, with detailed worked examples from the actuarial field. There are examples on examining and fitting distributions, modeling extreme value distributions, and fitting GLMs for stochastic reserving.  The data and scripts are also available for download.

R Toolkit: R Examples for Actuaries

R for Actuaries

The Society of Actuaries publishes a quarterly newsletter called CompAct, and since October 2008 it has included R Corner, a column of R tips for beginning actuarial users. The column is written by Steve Craighead, an actuarial consultant based in Atlanta. Columns so far have covered:

• Introduction to R (p24)
• Reading data files (p11)
• Data objects (p9)
• Models and model formulae (p14) 

Society of Actuaries: CompAct Electronic Newsletter (PDF archive)