Li's model sidestepped the problem of trying to correlate all the variables that determine risk. Instead, it based its assumptions on the historical dips and swells of the market itself. In essence, Li used the past to map the future. Full Story »
Posted by Kaizar Campwala
An interesting read, though the story doesn't go into what happened that his idea was allowed to propagate de-contextualized.
The side box explaining how the formula doesn't work is the most hopeful, but still muzzy and unclear. The mathematical assumptions used are not clear, nor is the set of assumptions that were invalid clearly identified. The culpability of financial institutions for failing to enlist competent math expertise is not presented.
1) Even statisticians can drown in a creek with an average depth of 2 inches. 2) Kaizar's linked article in Wired is much more readable and explanatory. 3) Bad assumptions of Normality, time invariance, and statistical independence are plentiful among the semi-literate in math.
A human touch is added to a very complex and difficult story. Excellent and clear writing about the bewildering economic collapse.
The Wa;ll Street traders didn't want to understand Mr. Li's formula and have to admit that it only predicted based on past experience -- it did not take into consideration possible future risks.The traders were able to mint money from it for themselves -- so no one wanted to ask hardquestions.
This is great journalism. This is what you learn when everybody cry's "what happened". If what Mr. Li says was, and believe me, I do not know, Is you learn from the past to fix the future. It was a theory. You cannot blame this whole mess on this one guy. I think?
Retrieving Comments
