[R] help with R

Peter Dalgaard p.dalgaard at biostat.ku.dk
Wed Jan 9 23:11:49 CET 2008

Sitadri_Bagchi at swissre.com wrote:
>  Folks, Two simple questions :
> (1) I have a data set (call it data.xls) in a folder in my hard drive. How 
> do I perform a simple regression between two variables from that data set? 
>  After I click on 'R', what exactly do I type in?
Ideally, you shouldn't really start from there (because transfer of data 
between different applications is not for beginners --  it is better to 
have your data in a text file with a well-defined format), but let's try:

a) Open the spreadsheet. Make sure that the 1st element of each column 
has the name of the variable. Let us assume that the 2 relevant ones are 
called "x" and "y".  Highlight the relevant region and copy to clipboard.

b) In R type

mydata <- read.delim2("clipboard")
plot(y~x, data=mydata)
summary(lm(y~x, data=mydata))

This assumes that you are using a German locale (comma is decimal 
separator), otherwise use read.delim("clipboard").

> (2) Where do I get to see the complete library of packages offered by R? 
> In particular, I am interested in quantile regression and logistic 
> regression.
> Thanks.
>                 Sitadri

   O__  ---- Peter Dalgaard             Øster Farimagsgade 5, Entr.B
  c/ /'_ --- Dept. of Biostatistics     PO Box 2099, 1014 Cph. K
 (*) \(*) -- University of Copenhagen   Denmark          Ph:  (+45) 35327918
~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk)                  FAX: (+45) 35327907

More information about the R-help mailing list