Saturday, December 4, 2010

On Models and Theories

At the Market Pipeline -- itself a potentially very useful site -- a link to a link to a 14-page PDF by Emanuel Derman of Columbia University.

Abstract:
Theories deal with the world on its own terms, absolutely. Models are metaphors, relative descriptions of the object of their attention that compare it to something similar already better understood via theories. Models are reductions in dimensionality that always simplify and sweep dirt under the rug. Theories tell you what something is. Models tell you merely what something is partially like.


I found the paper interesting. Two excerpts:

Models are analogies, and always describe something relative to something else. Theories, in contrast, are the real thing. They don’t compare; they describe the essence, without reference.

It takes intuition to discover theories. Intuition may sound casual but it results from intimate knowledge acquired by careful observation and painstaking effort.

Can a hobbyist have intuition? I think so.

2 comments:

Jerry said...

This isn't directly relevant, but it's interesting. This guy was able to, via some kind of genetic computer algorithm, deduce Newton's Law just by observing the motion of a pendulum. Theory - with no intuition required. :)
http://www.guardian.co.uk/science/2009/apr/02/eureka-laws-nature-artificial-intelligence-ai
http://ccsl.mae.cornell.edu/sites/default/files/Science09_Schmidt.pdf

He's got it up for download here: http://ccsl.mae.cornell.edu/eureqa - might be worth trying that approach out on "the economy" over the holiday! heh. (i.e. http://xkcd.com/793/)

The Arthurian said...

WOW! I bet that thing could easily re-create the Taylor Rule.