[R] How to Describe R to Finance People

[Frank E Harrell Jr]

Ko-Kang Kevin Wang wrote:
> Hi,
> 
> I've been doing a joint research with someone from the Property
> Department here and she is about to give a presentation on the
> results.  The audience will include people from Property and Finance,
> and she is wondering how to describe R to these people (as I used R to
> do the analyses), since she has never even heard of R before our joint
> research (and has been using SPSS).  The difficult part is she has
> only about 1 ~ 2 minutes to talk about R.
> 
> The following is what I have in mind, any suggestions from people in
> Finance will be greatly appreciated!  (From our research together I
> think it may be safe to assume the audience will know, or at least
> have heard of, basic statistical terminology such as multiple linear
> regression and dummy variables).
> 
> \begin{quote}
> R was originally developed by Dr. Ross Ihaka and Dr. Robert Gentleman
> from the Department of Statistics at the University of Auckland in
> 1992.  It is free and in the last decade it has evolved into one of
> the most powerful statistical software, with over 150 user-contributed
> add-on packages.  It is not only used by statisticians or scientists,
> but also econometricians and people in finance due to its cost (FREE)
> and its powerfulness.

You might say that many professional statisticians consider R to be the 
premier statistical software system.

> 
> Although it has a slightly higher learning curve than SPSS-like
> program, it gets easier to use once one is familiar with it.  One of
> the main advantage it has over SPSS-like software is that you do not
> need to explicitly create dummy variables.  You only need to specify
> your dependent variable and independent variables and R will fit it
> (and create dummy variables automatically) for you.

You might mention that transformations may be specified on the fly in 
general, e.g. sqrt(y) ~ x1 + log(x2) in any model.

Sometimes in a presentation (when more time is available) I spend a few 
minutes touting the advantages of command languages even for things in 
which most people think that a WYSIWYG interface is superior.  A good 
example of this is graphviz for drawing diagrams.  I cover this in 
http://biostat.mc.vanderbilt.edu/twiki/pub/Main/StatCompCourse/sCompGraph.pdf.

This relates to reproducible analysis which is also surveyed in those notes.

Frank Harrell

> 
> It also has many state-of-art free resources, including manuals,
> contributed tutorials and documentations, online.  A free mailing list
> is also available for people to ask questions and questions are
> usually answered by more experienced users around the world within a
> few hours (sometimes even within minutes).
> \end{quote}
> 
> As mentioned above, she was rather impressed when I mention that one
> does not need to create dummy variables in R.  Therefore I am thinking
> she might be interested in mentioning it in her talk.
> 
> I have never had experience of trying to introduce R to
> non-Scientists, hence I would appreciate any comments!
> 
> Cheers,
> 
> Kevin
> 
> --------------------------------------------
> Ko-Kang Kevin Wang, MSc(Hon)
> SLC Stats Workshops Co-ordinator
> The University of Auckland
> New Zealand
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://www.stat.math.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
> 


-- 
Frank E Harrell Jr   Professor and Chair           School of Medicine
                      Department of Biostatistics   Vanderbilt University