A quickie on philosophy of modeling

2009 November 23
by Daniel Lakeland

People making models can learn a lot from Jorge Luis Borges’ Celestial Emporium of Benevolent Knowledge’s Taxonomy

These ambiguities, redundancies, and deficiencies recall those attributed by Dr. Franz Kuhn to a certain Chinese encyclopedia called the Heavenly Emporium of Benevolent Knowledge. In its distant pages it is written that animals are divided into

(a) those that belong to the emperor;(b) embalmed ones; (c) those that are trained; (d) suckling pigs; (e) mermaids; (f) fabulous ones; (g) stray dogs; (h) those that are included in this classification; (i) those that tremble as if they were mad; (j) innumerable ones; (k) those drawn with a very fine camel’s-hair brush; (l) etcetera; (m) those that have just broken the flower vase; (n) those that at a distance resemble flies.

(Jorge Luis Borges – The Analytical Language of John Wilkins)

When I worked at Jax Kneppers Associates, this was my favorite piece of literature to trot out. When attempting to claim damages in lawsuits, the plaintiffs would always employ this form of classification, for if every little problem is unique, there can be nothing said about their general character.

Modeling is essentially the opposite of this, we attempt to find the commonality in many different observations. It is data that is like the compendium: little tidbits of information put together into a collection.

The joy of modeling is extracting the juice out of data.

As I’ve always said, what makes a statistician look good is not teasing out a small effect, but finding a huge effect that hasn’t been noticed before.

(Andrew Gelman)

One Response

Trackbacks and Pingbacks

  1. Assorted Links « Permutations

Comments are closed.