Jeff Rasmussen <[EMAIL PROTECTED]> wrote:
> I tried to subtlety nudge the Pro-Bunk side to look at Quantum Physics and
>Heisenberg's Uncertainty Principle as well as Eastern Philosophies, but I was too
>subtle as they didn't pursue those. In the future, if I teach the course, I'll
>require some coverage of those area. In brief, a compelling arguments can be made
>that the reliance on Objectivity, Independent and Dependent Variables, the Null
>Hypothesis and so forth are really quite nonsensical. Like Newtonian Physics, they
>seem to work okay, but w
hen pushed they collapse. Fritoj Capra's "Tao of Physics" does a good job in showing
how the current Western model of science as it was used in Physics (and is used in
Psychology) is nonfunctional.
I think this ultimately comes down to George Box's famous quip that all
models are wrong, but some models are useful. Statistical theory deals
with idealized constructs that don't exactly exist in the real world, but
approximate real-world phenomena closely enough that it's possible to get
useful work done. I'd go further and say that a model *has* to be wrong
(in the sense of incompleteness rather than inconsistency) in order for it
to be useful; a model that corresponds exactly to reality is as complex as
reality itself, which for anything non-trivial means that it's to complex
for humans to deal with.
You might also want to touch on operationalism (W. Edwards Deming's
writings would be good introductions). The Florida election would be a
good example to use: to an operationalist, it's completely meaningless to
talk about the True Vote without reference to how the vote is counted, and
it would be nonsense to compare counting methods based on how close they
get to the "true" totals.
=================================================================
Instructions for joining and leaving this list and remarks about
the problem of INAPPROPRIATE MESSAGES are available at
http://jse.stat.ncsu.edu/
=================================================================
