How the Gaussian copula got adopted
In December 2008, Sam Jones of the FT was kind enough to mention the Gaussian copula function to me. That mention eventually became my Wired magazine cover story, and I always felt a little bit guilty about my story coming out first, since I knew that Sam was working on one too.
Well, Sam’s feature on the copula has now appeared, and it takes a rather different tack than mine; in any case, it’s a great read, so do check it out. Here’s one thing I learned from reading it:
On August 10 2004, the rating agency Moodyâ€™s incorporated Liâ€™s Gaussian copula default function formula into its rating methodology for collateralised debt obligations, the structured finance instruments that subsequently proved the nemesis of so many banks. Previously, Moodyâ€™s had insisted that CDOs meet a diversity score â€“ that is, that each should contain different types of assets, such as commercial mortgages, student loans and credit card debts, as well as the popular subprime debt. This was standard investing good practice, where the best way to guard against risk is to avoid putting all your eggs in one basket. But Liâ€™s formula meant Moodyâ€™s now had a model that enabled it to gauge the interrelatedness of risks â€“ and that traditional good practice could be thrown out of the window, since risk could be measured with mathematical certainty. No need to spread your eggs across baskets if you knew the exact odds of your one basket being dropped. A week after Moodyâ€™s, the worldâ€™s other large rating agency, Standard & Poorâ€™s, changed its methodology, too.
They’re like Sotheby’s and Christie’s, those two. I’m not sure that “criminal” isn’t too strong a word for the way in which they offer no real alternative to each other, instead chosing to ape whatever the other one does.