[ View menu ]

Predictions, theories, and dangerous things

Filed in Books ,Ideas ,Profiles
Subscribe to Decision Science News by Email (one email per week, easy unsubscribe)


Making predictions is risky business. If you make a claim like “Dow 30,000 by 2008“, it’s more than a little embarrassing when you’re wrong. (If you’re wondering, the Dow’s peak was just over 14,000).

But making predictions is important. Science, for instance, suffers when theories are vague and when models have so many free parameters they can never be falsified. As it has been said in the classic book Plans and the Structure of Behavior:

A good scientist can draw an elephant with three parameters, and with four he can tie a knot in its tail.

In other words, if your theory is so general-purpose that you can draw an elephant with it, what picture can’t you draw with it?

(Incidentally, I get this quote from Seidenberg who good naturedly says that one of his own quarter-million-edge neural networks “can presumably draw every hair on the elephant’s back”).

In Nassim Taleb’s book The Black Swan: The Impact of the Highly Improbable and quite a few interviews, he went on record to say that the prevailing conditions were a powder keg. Have a listen to these interviews from him (from the EconTalk podcast series) before and after the mess:

Pre-Downturn (April 30, 2007). Dow Jones closed at 13,063.
Taleb on Black Swans

Post-Downturn (March 23, 2009). Dow Jones closed at 7,776.
Taleb on the Financial Crisis

Photo credit:http://www.flickr.com/photos/great_driffield/4263493722/


No comments

RSS feed Comments

Write Comment

XHTML: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>