[R] Newbie question: what are the advantages?
M. Edward (Ed) Borasky
znmeb at aracnet.com
Tue Feb 27 03:56:47 CET 2001
On Mon, 26 Feb 2001, Thomas Lumley wrote:
> On Tue, 27 Feb 2001, hzi wrote:
> > What are the advantages of using R when compared? Is flexibility an
> > issue? What about the learning curve? Is it something that is awfully
> > hard to learn? And the documentation seems to be rather sparse, unless
> > you´re willling to buy a book (no, I´m not some "cheap" person, I´m a
> > student from Brazil - things are not so cheap for me...which is one of
> > the reasons free software is attractive to me).
> Flexibility is one major advantage of R over SPSS. It also has better
> `publication-quality' graphics. It's easier to do simple things in SPSS,
> but probably harder to do complicated things.
> The available documentation isn't that bad, if you start with
> "Introduction to R" and then some of the contributed documentation on
> cran.r-project.org. Learning to use statistical procedures that you
> understand fairly well is pretty straightforward. Learning to use
> procedures you don't understand at all can be much harder, but that might
> be regarded as a feature. I'd say that if you can use Linux you should be
> able to cope with R.
I used to use Excel for the simple stuff (linear regression and histograms) and
Minitab for the complicated stuff (boxplots, mostly) at work (mostly having to
do with computer performance analysis), and Excel plus XLSTAT and ViSta for my
home projects, mostly having to do with computational finance. At work, I now
do almost everything in R, except for some things that require pre-processing of
massive datasets, which I do in Microsoft Access. Once I get RODBC up and
running, I'll be able to automate all of this. At home, I do everything in R.
It took me about a week to figure out how to do the histograms, kernel density
estimation, boxplots and lowess smoothing for the projects at work, and that
includes all the Perl code to collect the input data and drive R. The total
amount of R code for all this magic is less than 100 lines, including comments.
I never have been able to automate all of that with Minitab; the macro language
that comes with Minitab is virtually unreadable and not that much easier to
write. I'm an extremely happy R user!
znmeb at aracnet.com (M. Edward Borasky) http://www.aracnet.com/~znmeb
Actually, for their size, elephants don't smell all that bad.
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