Showing posts with label LTCM. Show all posts
Showing posts with label LTCM. Show all posts

Friday, August 19, 2011

Confessions of an Econometrician

From FIN Alternatives (bold emphasis added)

A co-founder of Long-Term Capital Management said that the legendary collapsed hedge fund’s leverage ensured its fate.

LTCM collapsed in 1998—a year after Myron Scholes won the Nobel Prize in economics—forcing the Federal Reserve to arrange a bailout. At the time, it was the largest-ever hedge fund failure.

Scholes, who went on to found hedge fund Platinum Grove Asset Management, now says that the firm’s leverage doomed it in the wake of Russia’s sovereign debt default.

“LTCM ran leveraged positions at too-high risk levels,” Scholes told Risk. “It was not a sustainable business in the longer run if you have to reduce leverage and seek extra capital at a time when risk transfer costs are high.”

And this risks inherent in LTCM’s portfolio were higher than anyone realized at the time.

“It was a much higher-probability event than people thought, because it told people they were going to make 40% a year at 20% volatility—a high risk level,” Scholes said of LTCM’s demise. “The problem comes because, as a hedge fund, you don’t really have deep pockets, so it’s hard to run at a high risk for a long time.”

Scholes also blamed an over-reliance on classic portfolio theory.

“Capital models should give levels that are required to sustain the business at times of shock, and this is different for leveraged hedge funds because they can’t call for additional capital from investors,” he told Risk. “I believe capital models should not rely on portfolio theory, because the correlation structure is just not constant—in a crisis, you have intermediaries reducing risk simultaneously, so things that appeared to be independent clusters in the past become correlated, and diversification against those clusters does not provide staying power.”

In short, taking too much risk via leverage based on the assumption of the infallibility of econometric models.

As the great Ludwig von Mises warned (bold emphasis mine)

But it is not permissible to argue in an analogous way with regard to the quantities we observe in the field of human action. These quantities are manifestly variable. Changes occurring in them plainly affect the result of our actions. Every quantity that we can observe is a historical event, a fact which cannot be fully described without specifying the time and geographical point.

The econometrician is unable to disprove this fact, which cuts the ground from under his reasoning. He cannot help admitting that there are no "behavior constants."

Wednesday, February 25, 2009

How Math Models Can Lead To Disaster

The crash of Wall Street had been aggravated by people looking for rationales to confirm their beliefs. And there was no better source of inspiration than one modeled after a seemingly impervious mathematical formula.

An article from Wired.com on “Recipe for Disaster: The Formula That Killed Wall Street” by Felix Salmon, gives a splendid narrative.

Some excerpts (all bold highlights mine),

``For five years, Li's formula, known as a Gaussian copula function, looked like an unambiguously positive breakthrough, a piece of financial technology that allowed hugely complex risks to be modeled with more ease and accuracy than ever before. With his brilliant spark of mathematical legerdemain, Li made it possible for traders to sell vast quantities of new securities, expanding financial markets to unimaginable levels.

``His method was adopted by everybody from bond investors and Wall Street banks to ratings agencies and regulators. And it became so deeply entrenched—and was making people so much money—that warnings about its limitations were largely ignored….

``It was a brilliant simplification of an intractable problem. And Li didn't just radically dumb down the difficulty of working out correlations; he decided not to even bother trying to map and calculate all the nearly infinite relationships between the various loans that made up a pool. What happens when the number of pool members increases or when you mix negative correlations with positive ones? Never mind all that, he said. The only thing that matters is the final correlation number—one clean, simple, all-sufficient figure that sums up everything.

``The effect on the securitization market was electric. Armed with Li's formula, Wall Street's quants saw a new world of possibilities. And the first thing they did was start creating a huge number of brand-new triple-A securities. Using Li's copula approach meant that ratings agencies like Moody's—or anybody wanting to model the risk of a tranche—no longer needed to puzzle over the underlying securities. All they needed was that correlation number, and out would come a rating telling them how safe or risky the tranche was…

``As a result, just about anything could be bundled and turned into a triple-A bond—corporate bonds, bank loans, mortgage-backed securities, whatever you liked.

``In the world of finance, too many quants see only the numbers before them and forget about the concrete reality the figures are supposed to represent. They think they can model just a few years' worth of data and come up with probabilities for things that may happen only once every 10,000 years. Then people invest on the basis of those probabilities, without stopping to wonder whether the numbers make any sense at all.

``As Li himself said of his own model: "The most dangerous part is when people believe everything coming out of it."

Some observations:

One. This is another example of people how people (including the majority of experts and professionals) fall prey to cognitive biases, such as the confirmation bias, in order to buttress their beliefs.

Two. This also shows of people’s penchant to trustingly espouse mathematical models to address the concerns of social structures especially in markets.

The illustrious Friedrich A. Hayek (1899–1992) in his Nobel Prize speech The Pretence of Knowledge warned of this, ``A theory of essentially complex phenomena must refer to a large number of particular facts; and to derive a prediction from it, or to test it, we have to ascertain all these particular facts. Once we succeeded in this there should be no particular difficulty about deriving testable predictions — with the help of modern computers it should be easy enough to insert these data into the appropriate blanks of the theoretical formulae and to derive a prediction. The real difficulty, to the solution of which science has little to contribute, and which is sometimes indeed insoluble, consists in the ascertainment of the particular facts.”

For pundits, math models elicit intellectual attraction of a system that can be deliberately controlled. However, the sad reality is that they hardly capture all variables required out of the complexity of the environment. And over reliance thereof may lead to disastrous consequences, similar to the LTCM fiasco.

And this applies not only to Wall Street but to the general economics or even to the environment.