[R-sig-finance] R vs. S-PLUS vs. SAS

Patrick Burns patrick at burns-stat.com
Thu Dec 2 21:41:38 CET 2004


There was just a thread on R-help about R versus SAS.  Your
summary that SAS' main advantage is better handling of large
datasets is similar to the comments in that thread.  (There was
some sentiment that SAS was better with mixed effects models,
but that is unlikely to come into play much in finance.)

In the old days with S-PLUS, the rule of thumb was that you
needed 10 times as much memory as your dataset.  By that
standard you could handle a 200 MB dataset if you have 2GB
of RAM.  R (and current versions of S-PLUS) are more frugal
than S-PLUS was back then.  The 10 times rule was pretty
much a worst case -- if you do simple things, then you are
unlikely to use as much memory.

Patrick Burns

Burns Statistics
patrick at burns-stat.com
+44 (0)20 8525 0696
http://www.burns-stat.com
(home of S Poetry and "A Guide for the Unwilling S User")

Hoon Kim wrote:

>Dear David
>
>I appreciate sharing your experience using R in
>finance.  I am also doing quant equity research and my
>main tool is SAS.  I do not have much experience with
>R at this stage and I am curious what is your opinion
>on R vs. SAS.  My perception is SAS is much better in
>handling large data sets, which is usually the case in
>quant equity modeling.  Historical backtesting data
>can be easily over several hundread megabites.  In my
>opinion, other than the capability of handling large
>data set in SAS, I think R is a more flexible
>programming language.
>
>Could you kindly share your thoughts with me on this
>issue?  Do you have any problem in handling large data
>sets in R?  How do you deal with large data set in R? 
>Do you have recommendation on handling those large
>data in R?
>
>Thanks again for sharing your thoughts.
>
>Best,
>
>Hoon Kim
>
>
>------------------------------
>
>Message: 3
>Date: Tue, 30 Nov 2004 11:06:01 -0500
>From: David Kane <dave at kanecap.com>
>Subject: Re: [R-sig-finance] R vs. S-PLUS
>To: "My Newletters Etc." <MySubs at 3wplace.com>
>Cc: r-sig-finance at stat.math.ethz.ch
>Message-ID:
><16812.39529.463769.246947 at gargle.gargle.HOWL>
>Content-Type: text/plain; charset=us-ascii
>
>My Newletters Etc. writes:
> > I'm wondering if you might be willing to share some
>specifics about
> > your use of R.  
>
>Of course. I am a real R evangalist.
>
> > For example, what types of analysis have you done
> > with R?  
>
>I work in quantitive global equity modeling. How much
>is a share of
>IBM worth? For me, the power in R is not so much that
>the statistical
>tools are fancier than what one find in SAS or Stata
>or whatever ---
>although this is often the case --- but that the
>programming language
>is richer and the production tools (especially
>packages and test
>cases) are so easy to use.
>
> > Have you used pre-defined "packages" or have you
>"rolled
> > your own?"  
>
>I use all sorts of R packages but, for the actual
>financial analysis
>parts, have had to role my own. It is on my to-do list
>to more fully
>explore things like Rmetrics. I am unaware of any
>packages devoted to
>the sort of stuff that I need to do regularly. As an
>example, I am
>today calculating growth rates of various sorts. Which
>company has the
>fastest growing sales? The answer to this question
>depends on all
>sorts of sticky points that reasonable people can
>disagree about.
>
> > Do you have any pointers about how to most
>effectively
> > approach learning R?  Hopefully these questions are
>sufficient
> > to give you a feel for the direction of my inquiry.
>
>The standard R documentation is a fine place to begin.
>I would start
>by reading An Introduction to R cover to cover (while
>doing the
>exercises) and then, depending on your level of
>computer experience,
>going on to Writing R Extensions.
>
>I encourage you to use R, especially in academics. To
>the extent that
>you believe, as I do, that research should be public
>and replication
>easy (see:
>http://gking.harvard.edu/replrepl/replrepl.html), R
>provides the perfect tool.
>
>
>  
>



More information about the R-sig-finance mailing list