« CRAN R 2.10.0 scheduled for October 26 | Main | How to use a Google Spreadsheet as data in R »

September 25, 2009


Feed You can follow this conversation by subscribing to the comment feed for this post.

Another reason to choose the line with one loaded cart when you have but a few items: the person with the loaded cart will usually offer that you go ahead since you have relatively few items...

I believe someone has done this study using scanner data, the Moretti and Mas "Peers at work" paper in:


The paper used the results to test whether there was peer pressure among cashiers. ( I admired the creativity of using scanner data, used generally to measure preferences only, as a source of timestamps.)



Right after I clicked "post," I realized that my contribution would be made a lot more positive by pointing out that there's publicly available scanner data (it may require an email asking for it) at the University of Chicago Business School Center for Marketing.

It may make an interesting exercise for a class on R in business analytics -- again, for the creative use of data that is usually used only for measuring preferences or response functions (to marketing actions).


I am most fascinated by the reading of data directly from a spreadsheet published in Google Docs. I have been using RGoogleDocs package which lets me read data but then I have to sign in.

I am fascinated by your line
shopping <- read.csv(
+ "http://spreadsheets.google.com/pub?key=tE9pXlYLwTAeiDWxL8h_viA&single=true&gid=0&range=A1%3AE37&output=csv",
+ as.is=TRUE)

Where I can I read more about the arguments (or whatever you call them, such as the "single", "gid", "range")?

Farrell, I got that link from Dan Meyer's post. I'll investigate more about how to read a Google Docs spreadsheet in R using this method, and post about it.

There was surprisingly little information on the Web on how to link to a Google Spreadsheet export, but I think I've figured it out.

I saw your post. Thank you very much.
RGoogleDocs is a little bit more of a pain but sometimes it is imperative that the data not by publicly available, or at least not yet.

The comments to this entry are closed.

R for the Enterprise

Got comments or suggestions for the blog editor?
Email David Smith.
Follow revodavid on Twitter Follow David on Twitter: @revodavid

Search Revolutions Blog