[R] Your opinions

DAVID JENSEN djense00 at yahoo.com
Wed Oct 23 00:03:15 CEST 2002

I am a long-time statistician and SAS programmer
interested in learning R or S-Plus.  I am intrigued by
being able to do statistical analysis in a more
interactive environment than I am used to in SAS, not
to mention using the much better and easier graphics
capabilities.  In other words I am tired of having to
develop a whole SAS program just to read some data in,
do an ANOVA and a scatterplot.  From what I have
learned of R/S-Plus it appears to be a whole lot
easier (and much more fun) to do things like this in
R/S-Plus than it is in SAS.  If it matters, I will be
running R or S-Plus in Windows 2000.  

For starters, I have access to both R 1.60 and S-Plus
2000 with the ability to obtain a low-cost student
license for S-Plus 6 in the near future if I decide
to.  So the availability of either system is the same.
 As an absolute beginner, I would like your opinions
on which environment would be preferable - R or
S-Plus.  Let's assume that I am willing to put in the
time and effort to make the obvious differences
between the two environments (the GUI interface in
S-Plus) a non-issue.  I am a programmer so I prefer to
learn and use the command-line interface anyway.  So
let's just say that I would very seldom use the GUI in
S-Plus anyway (that may or may not be true but I am
trying to make things equal in terms of the two
environments' capabilities rather than judging them by
how convienient they are).    

Is there a practical reason to choose R over S in
terms of functionality or efficiency?  I will have
some fairly large datasets (over 100,000 obs with 40
variables) but mostly smaller datasets with only a
couple thousand observations.  Am I better off, given
the fact that I have access to S-Plus to use it given
the built-in conveniences which include the GUI.  Or
is there a very practical reason to choose R, other
than the fact that I have great admiration for an
open-source software project and those who contribute
to it.  If I did not have the access I do to S-Plus,
it would be a no-brainer.  I would happily choose R. 
But given the fact I do have access to S-Plus, is
there a reason to instead choose R?  Is what I learn
to do in R directly applicable to S-Plus or are the
differences profound enough as to be confusing
switching back and forth?

Thanks so much in advance for your advice.



 the expert host your web site

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

More information about the R-help mailing list