On Fri, 25 Aug 2000, William Levine wrote:
> I am teaching an Introduction to Statistics course in psychology, and
> in class the other day, I brought up the issue that SAT scores and IQ
> scores may not really be interval scales.
Mmm. Well, Bill, if they aren't "really" interval scales, what do you
suppose them to be, "really", especially given the amount of time and
energy that have been devoted to trying to ensure that they are interval?
And, what difference does it make, practically, to the work assigned in
the course, and/or to the psychological and quantitative theory & practice
that your students will eventually be expected to understand, if not
indeed to have mastered?
> My TA pointed out that they are *standardized* tests,
That is true, and relevant.
> and that the intervals really are designed to mean something.
That may be true (and probably is), but I do not see its relevance to the
(pseudo-) issue of whether the resulting scores are interval.
> I came back with the comment that we really don't know what these
> tests measure.
So? Do we "really know" what any instruments measure?
Which instruments, and how do you justify your faith in them?
And what has that to do with whether the scores are interval?
> Without raising the specter of what IQ and SAT tests really measure,
> does anyone have any comments that might be helpful in telling students
> what to think about this?
Can't imagine what you were about in introducing the matter in the first
place. If your introductory students are anything like the ones I've
dealt with over the years, they have quite enough to do in learning to
make sense out of statistics as a discipline, without being distracted
by issues that are not unanimously agreed (a) among psychologists and
(b) among statisticians.
> Either that, or any references that discuss this issue explicitly.
What "this issue" is might be a bit ambiguous.
If you refer merely to the question of whether SAT and IQ scores may
reasonably be treated as though they were interval scales, even if you
happen not to believe that they are, that's one thing.
If you are trying to address the whole ball of wax involved in attempting
to force all imaginable variables into one or another arbitrary category,
with no recognition of the possibility that a variable may sometimes fit
one category and at other times may not, or that variables may quite
reasonably fall "between" categories as it were (the category system
commonly in use for this purpose is not exhaustive, although a great mort
of folks seem to think it is), that's another thing (or, really, set of
things) altogether.
(I do not suppose that these two possibilities exhaust the possible
meanings and purposes you had in mind.)
-- Don.
------------------------------------------------------------------------
Donald F. Burrill [EMAIL PROTECTED]
348 Hyde Hall, Plymouth State College, [EMAIL PROTECTED]
MSC #29, Plymouth, NH 03264 603-535-2597
184 Nashua Road, Bedford, NH 03110 603-471-7128
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
