On Thursday 02 February 2006 18:05, Walker, Russell
wrote:> I am interested in learning about people's experience with R training
or
> courses. What worked, what didn't? What do you recommend?
In the last few years I have been doing several short (around 10 hours)
courses on Data Mining using R. I've prepared them around the same ideas
that
guide the unfinished book I'm writing on the same topic
(http://www.liacc.up.pt/~ltorgo/DataMiningWithR/) , that is learning by case
studies. I think that for a tool like R, with a learning curve that people
tend to think as kind of steep, and for short courses, the hands on approach
is a good means to motivate students. This obviously requires properly
equipped classrooms but that is not difficult to get nowadays, particularly
when using free software as R. The feedback I got from these courses was
quite good and several students came back to me later on with further
questions which is a good indication that they continued their involvement
with R.
These courses were usually organized by proving short, non-demanding
introductions to the key concepts, and then followed by longer hands on
sessions where students try by themselves with real case studies. Because of
this I tend to prefer a short number of students (15-25) to increase the
interaction during the hands on parts. Still, I gave this course at last year
ACAI summer school (http://www.ktschool.org/) and eventhough there where
about 50 students the course was successful.
Regarding topics I tend to start by simple case studies where I can illustrate
basic concepts of data analysis using R together with the language itself,
and then select larger cases studies depending on the interests of the
audience.
Luis
--
Luis Torgo
FEP/LIACC, University of Porto Phone : (+351) 22 339 20 93
Machine Learning Group Fax : (+351) 22 339 20 99
R. de Ceuta, 118, 6o email : ltorgo at liacc.up.pt
4050-190 PORTO - PORTUGAL WWW : http://www.liacc.up.pt/~ltorgo