This page still under construction. Don't look yet. Or you can look, but be warned it's unfinished.
R is a general purpose computing language especially designed for statistics. For more info on R, see the R archive. There it says
R, also known as `GNU S', is a system for statistical computation and graphics. It consists of a language plus a run-time environment with graphics, a debugger, access to certain system functions, and the ability to run programs stored in script files. R implements a language which is not entirely unlike the S language developed at AT&T Bell Laboratories by Rick Becker, John Chambers and Allan Wilks. Indeed in the absence of an R manual, you can (mostly) get along by using the S manual.
The S computing language was invented by a group at Bell Labs (that's why its name is only one letter like C). It still is an active research project at Bell Labs. S is marketed by Insightful Corporation under the name S-PLUS. Although S-PLUS contains extra features added by Insightful (and its predecessor companies Mathsoft and Statistical Science Inc.), the core language comes from Bell Labs.
R is 80 to 90% compatible with S (S-PLUS). Some incompatibilities are
deliberate design decisions (see the
R FAQ
under What are the differences between R and S?
).
Some are features of S (S-PLUS) that the R team have not yet implemented.
To run R on a UNIX computer in the School of Statistics, just say
at a UNIX prompt. To get out (as with S),
say R
at an R prompt. To get the on-line
help either do
q()
help.start()
at an R prompt. Or just go to to the URL
http://rweb.stat.umn.edu/R/doc/html/
with any web browser.
Rweb is an implementation of R that can be run over the web. For more info on Rweb see the Rweb home page.
Our local Rweb server is on a different web server from these pages
http://rweb.stat.umn.edu/Rweb/
(note rweb.stat.umn.edu
rather
than www.stat.umn.edu
). The documentation for the version
of R used on the server is at the URL
http://rweb.stat.umn.edu/R/doc/html/
and this should always be the same version of R as is on the department workstations.
To run Rweb, you type some statements in the R language into the "R commands" window below and click "submit". The commands will be executed and the results displayed on a new web page. When you've looked at that page all you want, click the "back" button on your browser to return here.
A simple bit of R is any arithmetic expression. You can use it as a calculator. If you type "2 + 2" in the "R Commands" window and click "submit", Rweb will reply
Rweb:> 2 + 2 [1] 4
The "Dataset URL" window allows you to type in a URL that contains an R dataset. For example if you type
http://www.stat.umn.edu/geyer/somedata
in the "Dataset URL" window and
plot(x, y) out <- lm(x ~ y) summary(out) abline(out)
in the "R Commands" window, and click "submit", you get a scatter plot with regression line for the data in that dataset.
Questions or comments to: Charles Geyer charlie@stat.umn.edu