A Fifth R

Last week, Dr. Isabelle Côté reminded us of the importance of R’s in science: That is, Reading, (w)Riting, and ‘Rithmetic, plus the ability to Relate your work to others. There is one final R, and that is… well R itself.

R is statistical software that gives you a framework for analyzing, plotting, and ultimately understanding the data that you collect (you may be familiar with some of the more abstract uses of R if you read the blog regularly). Unlike most statistics programs, it is completely free, and is driven by a vibrant online community. If you pursue a career in science, the time will come where you need to use R. It is already the gold standard for biology, but is expanding into other disciplines as well (See this old but good article in the NYT).

Aside from being free, R is ideal because it is infinitely expandable. It has a system where people can write mini-programs called “packages” that any user can download and install. These packages add features to R which range from enhanced graphing capabilities, tools for complicated analysis, or even software which turns R into a GIS engine (like ArcGIS). With this expandability, R-savvy scientists may never have to pay for data analysis ever again.

However, for people with no background in programming (myself included) learning R can be a daunting task. It has no Graphical User Interface (GUI), so everything must be done using R’s scripting language. This is worth learning, and there are many great references including books (Intro to R), websites (Quick-R, Stack Exchange, R Gallery, and R-Bloggers) and online courses (http://blog.revolutionanalytics.com/courses/) to help with the process.

If you aren’t ready to commit to learning a new language, you can still experience some of R’s power through the use of Deducer, a GUI package that turns R into a point-and-click stats program similar to SPSS (www.deducer.org). It is based on the powerful ggplot2 graphing engine, meaning that you can use this program to make beautiful figures without knowing anything about how the coding works.

Better still, there is a one-click download which installs R, Deducer, and other supporting files all at once, which can be found at Deducer’s website (www.deducer.org). The site also contains a wiki and video tutorials to help you get up and running:

Deducer is no substitute for learning how to code in R. While it does basic plotting very well, you will find that you will be stuck with having to learn coding anyway as soon as you want to do anything outside of what’s capable in the GUI’s menus. However, it makes a great stepping-stone, and is more than enough for most analyses done in student projects here at BMSC.

It is critically important for modern scientists to be comfortable with analyzing and plotting the data they collect. As biologists, we do these tasks in R, and that is unlikely to change in the forseeable future. Deducer makes R accessible, and is an excellent option for courses which require students to work with data they collect in their research projects.

Happy plotting!

Brett Favaro
Ph.D Candidate, Earth to Ocean Research Group
 bfavaro@sfu.ca, @brettfavaro

<i>Editor’s note: As of 18:05 June 11, the CRAN website for SFU (canada BC) is down, so try a different one if you are playing with R 🙂

Advertisements

One thought on “A Fifth R

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s