Skip to content

How would you do a logistic analysis

3 messages · chromatonus 712, Brian Ripley, Ott Toomet

#
On two lists of data (in a matrix perhaps?) And may i also know where I can 
find the complete documentation of how to use all the functions in R? Thank 
you for your help!


_________________________________________________________________



-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
#
On Thu, 29 Aug 2002, chromatonus 712 wrote:

            
Lists and matrices are different things, so please be more precise.
In refman.pdf.  You may need to do

make pdf
make install-pdf

though to get it installed.

Good reading (it is over 1000 A4 pages).
#
On Thu, 29 Aug 2002, chromatonus 712 wrote:
|On two lists of data (in a matrix perhaps?) And may i also know where I can 
  |find the complete documentation of how to use all the functions in R? Thank 
  |you for your help!

It seems that you need to start with ,,an introduction to R'', available at
CRAN (R website) where it is made clear what is list, what is matrix and how
to do anayses with them (there is also mentioned logit).

You need to do something like

glm(y ~ x1 + x2, family=binomial(link=logit))

where x1 and x2 are explanatory variables and y are responses.  Note this is
binomial logit, I have not seen any package able to do multinomial or nested
logit.  There are however many methods for multinominal analysis,
unfortunately I am not familiar with them.

You can download complete R reference manual from CRAN, but I would rather
use a html-form of it (html form should be installed by default).

Cheers,

Ott

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._