[R] Are you experienced in SAS and R as well? Which of these would you recommend me?

Frank E Harrell Jr fharrell at virginia.edu
Fri Nov 23 14:47:32 CET 2001


Jon you said that beautifully.  I want to emphasize one of your excellent points.  I have seen a big difference in the depth of statistical analysis accomplished by SAS users as opposed to S-Plus or R users.  SAS users seem to be more content with "off the shelf" analyses, and sub-standard model diagnostics.  Also in agreement with you, SAS is not really all that easy to learn.  Part of that is due to the separation of DATA and PROC steps.  But on the other hand since the average statistician doesn't try to get too fancy with SAS, there are fewer things to learn.

What got me instantly converted from SAS to S-Plus in 1991 when I visited Terry Therneau at Mayo Clinic is that he was using S-Plus routinely to do second-order analyses such as bootstrapping a stepwise variable selection procedure to show its volatility on the medical researcher's own dataset.

Frank Harrell

On Fri, 23 Nov 2001 08:02:09 -0500 (EST)
Jonathan Baron <baron at cattell.psych.upenn.edu> wrote:

> >From: "micha fuchs" <michafuchs at hotmail.com>
> >Subject: [R] Are you experienced in SAS and R as well? Which of
> these would you recommend me?
> >
> >Disapointed about SPSS I have to choose another statistic program. And 
> >altough I sympathise with the idea of a non-commercial software-project like 
> >R and I like the spirit of the R community (and of course I am not keen on 
> >paying 150$ to SAS for a one-year students license), I will probably buy 
> >SAS, because people I will work with use SAS and I want a close cooperation 
> >with them. Besides I guess that SAS is still much more powerful than SAS.
> >
> >But: can t you convince me to choose R? I would appreciate
> that very much, 
> >because my sympathy is with the r-project. Maybe the syntax of both programs 
> >is quite similar, so I will still be able to exchange a lot of experience 
> >with my SAS-using future collegues!? Or I could even convince the newcomers 
> >to swap to R!?
> >
> >If you know some arguments, I should consider for my decission, I am looking 
> >forward to hear (or read) of you!
> 
> First, thanks for sending text only, without the html (at least
> the second time).
> 
> In my department, many people use SAS, and I have used it myself
> (although I'm not an expert).  We have it on our Unix server,
> which avoids having to pay the annual license fee.
> 
> It seems to me that, in some ways, R and SAS are complementary,
> and it is good to know, and use, both, if you live in a world
> where people use SAS.  SAS seems to be used for maintaining large
> databases that many people work on.  It also has routines that
> aren't available (yet) for R.  It is used by people who have big
> grants, big labs, etc.  It works differently - more compiled
> code - and is thus faster for some tasks.
> 
> R is (really) easier to use.  The help is better.  It is easier
> to get to the "hello world" stage.  It can do things easily that
> are done with difficulty on SAS, such as simulations.  The
> graphics are excellent.  You get results quickly, and can correct
> your errors faster.  There are probably contributed packages for
> R that do things that SAS cannot do, although I don't know of
> any.  When I see people use SAS, what impresses me is how little
> exploration they do, compared to what I do when I use R.  It is
> as if each analysis is a big deal, like the old days when SAS
> worked with (literally) punched cards.  I don't know if this is a
> necessary part of using SAS, but that is just my impression.
> 
> The syntax is NOT that similar, but the real difficulty that most
> people have is in learning to use ANY syntax.  In a way, then,
> the lack of similarity will make it easier to keep them separate,
> and you will still get the benefits of positive transfer from the
> idea of writing a program.
> 
> Best of all, both programs deal well with ascii data in standard
> formats, so you can use both on the same data.
> 
> So, my recommendation - which I make to students here too - is to
> learn R, and use SAS too if your colleagues use it.
> 
> Jon Baron (Prof. of Psychology, U. of Penna.)
> 
> -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
> 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
> _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._


-- 
Frank E Harrell Jr              Prof. of Biostatistics & Statistics
Div. of Biostatistics & Epidem. Dept. of Health Evaluation Sciences
U. Virginia School of Medicine  http://hesweb1.med.virginia.edu/biostat
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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