Gus Gassmann wrote:
> Stan Brown wrote:
>
> > Another instructor and I gave the same exam to our sections of a
> > course. Here's a summary of the results:
> >
> > Section A: n=20, mean=56.1, median=52.5, standard dev=20.1
> > Section B: n=23 mean=73.0, median=70.0, standard dev=21.6
> >
> > Now, they certainly _look_ different. (If it's of any valid I can
> > post the 20+23 raw data.) If I treat them as samples of two
> > populations -- which I'm not at all sure is valid -- I can compute
> > 90% confidence intervals as follows:
> >
> > Class A: 48.3 < mu < 63.8
> > Class B: 65.4 < mu < 80.9
> >
> > As I say, I have major qualms about whether this computation means
> > anything. So let me pose my question: given the two sets of results
> > shown earlier, _is_ there a valid statistical method to say whether
> > one class really is learning the subject better than the other, and
> > by how much?
>
> Before you jump out of a window, you should ask yourself if there
> is any reason to suspect that the samples should be homogeneous
> (assuming equal learning). Remember that the students are often
> self-selected into the sections, and the reasons for selecting one
> section over the other may well be correlated with learning styles
> and/or scholastic achievements.
Speaking as someone who does a lot of psychometrics, is there any reason
to believe you have a reliable test?
Reliable in the technical psychometric term that is? That is the first
and most important question. We will ignore the question of validity :)
Are you and your associate using the same test? You say so but is there
any chance of minor modifications? Even in the instrutcions ? Sorry to
be so picky but it can be important.
Are you sure that you and the other instructor are teaching the same
things (especially as to what will be on the exam?) Yes students do form
exam strategies.
--
------------------
John Kane
The Rideau Lakes, Ontario Canada
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
