resources
general good stuff
- The course text, Collaborative Statistics by Illowsky and Dean.
- The other course text, OpenIntro Statistics. We'll be using the second edition, downloadable from that link.
- Introduction to Probabability and Statistics Using R is another good resource. It's pitched at a higher level than Collaborative Stats and OpenIntro Stats and it's not complete, but we'll be using some sections and if it suits your style you can probably replace most of readings with material from this book. Another similar one is Verzani's Simple R.
- Pretty much any Big Book of Intro Stats will cover much the same material as we are covering. Feel free to browse the shelves in my office or the library to see if there is one that you like. In the past at Marlboro we've successfully used Moore's Basic Practice of Statistics and Bluman's Elementary Statistics. I'd say the former was a little better for learning from as an introductory text and the latter would do a better job as a reference book on a shelf if you suspect you'll be using statistical methods her and there over the years and will need your memory jogging.
- Some online stats tools (not R).
R and ggplot2
- The R Project Homepage from which you can download R and access the Introduction to R (pdf) in an online format.
- The in-built help system is good. To access the page about using "pie" for example, simply type "?pie" and hit return.
- Try R Code School seems to be a nice general introduction to using R. If you're a programmer already, you might prefer the youtube videos from Roger Peng for the Computing for Data Analysis Coursera course (if you're not already a programmer, these videos are not the place to start learning R).
- I've heard good things (but haven't looked at them myself) about R Twotorials, two minute videos that cover some specific thing you might want to do in R. Looking at the titles I think they're mostly more advanced than we'll need but you might find something useful.
- A sequence of online R tutorials by K. Black.
- The R Cookbook, a nice guide that takes an approach that I think is very much in keeping with the class, is (or will be soon) on the reserve shelf in the library.
- Googling specific topics can be very successful. Sites I've never gone to as a first step but are regularly very helpful and among my first choices to check out, other things being equal, when they show up in response to a query:
- I haven't played with it much yet, but RSeek is a search engine designed to look for R-related material.
- R-bloggers is a blog aggregator. Lots of interesting posts come through; worth checking every day or two if you get enthusiastic about R. Also a good place to search for what people have done with a particular topic/issue.
- A good collection of many of the standard graph types and how to create them with ggplot2
descriptive stats
probability theory
inferential stats
miscellaneous
bits and bobs from class
I'll upload R code and data files here, and anything else that is relevant from class sessions as well. Note that the R code especially is not guaranteed (or even likely) to be tidy. Most of the time the commenting will happen in class and I'll upload it here for you to play with rather than them being exemplars of How To Do It.
Tuesday Jan 29th
The cookie data file, in csv format, is linked below as cookieData.csv and the text file with the R commands are in cookie.r.
Thursday Jan 31st
R commands to do with the heights of soccer players, as per Example 2.7 of Coll Stats, is in soccerheight.r, attached below.
Thursday Feb 7th
The R commands we used to look at Anscombe's Quartet are attached as anscombe.r; the heating oil graphing commands are attached as oil2011.r
Tuesday Feb 12th
Thursday Feb 14th
Data (in .csv files) and R code (in .r files) attached below.
Tuesday Feb 19th
The commands we used in class on the librarian data, plus the extra tidying up I promised, are attached below as feb19.r.
Thursday Feb 21st
Thursday Feb 28th
The R file from today's class is attached as prob.r.
Thursday Mar 7th
The R file from today's class is attached as pig.r.
Tuesday Mar 12th
Today's R file attached: clt.r.
Thursday Apr 4th
Today's R file is apr4.txt.
Tuesday May 7th
Today's R file is may7.r