Introduction to using R in research

May 13, 2010
By

(This article was first published on Psychological Statistics, and kindly contributed to R-bloggers)

I was recently asked to give a talk to our graduate school annual conference. I offered several titles and the one they picked was Using R in research. I'm not sure if this was a good idea or not. The graduate school covers PhD students across three areas of the university: social sciences (including psychology), law and business. In addition the students tend to specialize in either qualitative or quantitive research methods, so I was talking to an audience who might know nothing about statistics or a great deal (e.g., several students have completed MSc courses in psychological research methods here or elsewhere).



My solution was try and explain the advantages of R relative to alternatives such as SPSS (probably the most common statistic package in the University). I also focussed a lot on graphical methods and simulation. It seemed to go quite well, but I worry that quite a few members of the audience were overwhelmed by large chunks of it.

I promised to put my slides on my blog - though I am not sure how useful they are to anybody who wasn't there. Without my commentary some (possibly most) of the slides won't make much sense. I spent a good deal of the time talking through exploratory plots of one data set (from Hayden, 2005). I use this example a lot in teaching and it involves a bit of class participating (guessing the origin of the data) - so I won't go into to detail here (lest I spoil it for future students), but you can google the original article if you are curious. I also spent some time on how R works (e.g., object types, assignment, basic modeling, plotting functions). My reasoning was that many of the audience have no familiarity with non-GUI interfaces in software and without explaining the basics of the interface they will not have the faintest clue how R works. For those with some familiarity (e.g., SPSS syntax) the examples were selected to show how powerful R can be for things like exploratory graphics.

Several students ask about resources for learning R. I mentioned some in earlier blog posts, but for psychologists Li and Baron's web resources are a good place to start. The other major resource is probably Quick R, but there are hundreds of other places to look online (depending on what stuff you need most).

To leave a comment for the author, please follow the link and comment on his blog: Psychological Statistics.

R-bloggers.com offers daily e-mail updates about R news and tutorials on topics such as: visualization (ggplot2, Boxplots, maps, animation), programming (RStudio, Sweave, LaTeX, SQL, Eclipse, git, hadoop, Web Scraping) statistics (regression, PCA, time series, trading) and more...



If you got this far, why not subscribe for updates from the site? Choose your flavor: e-mail, twitter, RSS, or facebook...

Comments are closed.