[R-sig-teaching] Online resources for teaching intro stats using R

[Douglas Bates]

On 10/8/07, Robert W. Hayden <hayden at mv.mv.com> wrote:
> Forwarded message: From: "Douglas Bates" <bates at stat.wisc.edu>
> >
> > I also see R as a way of removing some of the material in our courses
> > that is no longer necessary.
>
> I have worked with textbook publishers and I think the catch here is
> that they want to include as large a market as possible.  So if you
> write a text integrating R, it won't sell to those using SPSS.  The
> net effect is that texts are stuck at the NO-technology level, afraid
> to adopt anything.

That wasn't my point.  I really don't care what textbook publishers
think or do.  If the Department of Commerce had a list of endangered
industries, like the EPA's list of endangered species, textbook
publishers would rank just behind the recording industry.  They have
behaved arrogantly and avariciously (one of the main commentaries on
the production and marketing of textbooks is called "Ripoff 101" -
just Google for the title) and their industry is based on the
assumption that they will continue to make money delivering
intellectual content in a physical form to a captive audience.  Sound
familiar?  Their main enhancement of late is the idea that they will
include CD's as supplements to the books they sell to students.  Wow!
Selling CD's to students - now there's a growth market for you!

The other idea that textbook publishers seem to have is that they will
provide online course management systems tied to their textbooks.
Again, they miss the point.  My university provides me with a very
nice course management system (admittedly, I work at a research
university which would be expected to be an early adopter of such
technologies but more widespread use of this technology is just a
matter of time) and I don't need the publishers' course management
systems.  The publishers feel that they have experience in managing
content and that is all that is needed.  Managing content is the easy
part - managing access is the tricky part and my university does that
very well for me because they have the class registration records.

I am saying that as instructors we should examine carefully what we
teach and how we teach it.  We don't want to blindly follow every
passing fad but it is equally true that we are doomed if we assume
that everything will stay exactly the same as it was when I took an
intro stats course and, obviously, there is no need to adapt.

We are holding this discussion on the R-SIG-Teaching list.  The R
Project has created a fundamental change in the way that statistics
software is created and distributed and, to me at least, that has been
an incredibly positive change.  The R Project is a self-organizing
community.  There is no "R, Inc." (there is the R Foundation but that
was created primarily so that there is a legal entity to be the
copyright holder).  The content creators also control the
dissemination system.

This self-organizing aspect is a sea change in the way we do things.
For example, Di Cook and others are Iowa State did a wonderful job of
organizing the useR!2007 conference last August and did it without any
parent or umbrella organization.  They just created the conference.
There were sponsors but they came after the conference organization
was underway, not before.   I characterized the organizational
structure as "Hey, kids, let's hold a conference - we could use that
old barn over there."

What I am asking people to think about is what is the equivalent of
the R Project for online resources in teaching intro stats?  Is it
like wikipedia?  Is it more top-down than bottom-up?  Will it be a
free-for-all like "the blogosphere" as a new form of journalism? Is
there a chance for a self-organizing community to spring up and, if
so, how can it be nurtured?  Do people know of such initiatives in
other disciplines?  Are online journals a model?

Discuss.


> I like to teach statistics by bringing a data set
> to class and providing an analysis there.  The useful stuff that
> appears in textbooks is then footnotes along the way.  I'd like to
> write a textbook that works this way, but it would have to use some
> specific software, and publishers don't want that.  I have thought of
> creating something and just putting it on the WWW, in the manner of
> Jim Hefferon's linear algebra textbook:
>
>     http://joshua.smcvt.edu/linearalgebra/
>
> just down the road from me.
>
>
>  _______
> |   ^  |
> |     /                     Robert W. Hayden
> |    |                      in the old library
> |    |                      212 Main Street
> |   /                       P. O. Box 450
> |  |                      ^ North Troy, VT 05859
> L__L                        (802) 988-2587
>                             http://statland.org/
> Map of VT                   bob at statland.org
>
> Communications sent to Plymouth State will not reach me.
>
> _______________________________________________
> R-sig-teaching at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-teaching
>