[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: Stata vs SPSS
I agree that this is often a question of non-GUI vs. GUI, at least in the
minds of students. I taught a course a year ago in which undergraduates
were expected to conduct statistical analysis. I decided to use Stata and
teach via commands, mainly I decided this because when I talk with
students who learned via a GUI interface it seems they have a very rigid,
static understanding of data that is something out there they are given,
rather than a fluid, dynamic via of data as something they construct and
mold so as to address their queston. I am not saying anyone else has this
experience, I am just saying it has been my experience. So, I decided to
teach sans GUI.
The social science course required students to construct a question,
locate data (usually via the ICPSR depository), and get the data in shape
to analyze. Then, over several weeks, I introduced them to a series of
univariate and multivariate techniques, including OLS regression, logits
and probits. The emphasis was on intuitive understanding, not rigorous
In teaching the course I would routinely display the code on a
large-screen projector system; other times I would write code on the
whiteboard. I would also ask them to include the code in their problem
At the start of the term they were surprised to learn that we could do
anything without a GUI. By the end of the term they were excited about
the easy flexibility of just writing code.
I believe the learning curve is steeper for writing commands. But the
view from the summit is far grander. My students seemed to agree.
On Mon, 16 Oct 2006 email@example.com wrote:
> Can SPSS be used entirely from a command-line interface? If so, it would
> be interesting to see your students' reactions if you allowed SPSS, but
> only via command-line--no mouse-clicking. In other words, required them
> to submit the SPSS equivalent of do-files. This would be a way of
> separating their love of SPSS (of which I am skeptical) from their love of
> pretty mouse-driven GUIs (which I am hypothesizing is more the issue.)
> > On 10/15/06, Richard Williams <Richard.A.Williams.firstname.lastname@example.org> wrote:
> >> However, I suspect that isn't the kind of thing your students were
> >> complaining about! Who are these people, what is the field of study,
> >> what sorts of things are they going to need to do in their future
> >> careers?
> > These are graduate students majoring in Nutrition or Epidemiology.
> > They are being trained primarily for academic research. They are going
> > to be expected to perform simple statistical analyses (t-test, etc.)
> > and data manipulation.
> > Raphael
> * For searches and help try:
> * http://www.stata.com/support/faqs/res/findit.html
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
* For searches and help try: