Monday, September 21, 2009

An Econometrician Rips Econometricians


“I just want people to stop and think for once. There is too much mathematics in this business," said Paul Wilmott in a Bloomberg Radio interview.

Wilmott is a London-based author and quantitative finance instructor.
"Mathematics to forecast how markets will behave can overlook errors in the models, leading to flawed predictions," he sad.

“People don’t really question those assumptions enough,” said Wilmott, who founded the Diploma in Mathematical Finance at Oxford University, according to his Web site. “If the assumptions are wrong, then obviously the models and what follows can be wrong as well.”

He then discuses the old days.

“You go back 20 years, and people running finance, they were maybe history graduates,” Wilmott said. Now, much of the industry is run by mathematicians, he said. “A lot of mathematicians do not have that common sense that the old guard had,” he said.

Wilmott is close to understanding the key problem. The real problem is that there are no constants in human action, so in order to create an equation, econometricians must assume a variable(s) that has been relatively stable for sometime is really a constant, which then becomes vulnerable to Wenzel's Observation #1:

Any variable has the potential to eventually start to dance. A dancing variable is one that no longer acts like a constant and moves considerably outside its previous assumed range of movement.
A dancing variable that was assumed to be a constant can then lead to the blowing up of an equation, a portfolio, a company or an economy.



  1. Jobless History Degree DudeSeptember 21, 2009 at 9:21 PM

    Looks like I got my history degree two decades late.

  2. Well, if dancing variables are bad, why can't Congress pass a law forbidding variables from dancing in the first place???