JPMorgan Silence on Risk Model Spurs Calls for Disclosure
By Bradley Keoun - Jul 10, 2012 12:00 AM ET
The dispute revolves around value-at-risk, the main and sometimes only empirical gauge that investors get as they try to fathom how much a bank could lose if its trading bets go bad. Wall Street firms routinely give only broad outlines of how their mathematicians calculate VaR, according to data compiled by Bloomberg, and almost nothing about changes in statistical assumptions or the prices they choose to feed into their models.
---That's because the calculation of trading risk involves choosing randomly from a set of input variables that are essentially INFINITE, leading to "Statistical Assumptions" that are all but meaningless and thus creating risk quotients that are essentially worthless.
Let's say you're playing roulette and betting on red - you can calculate the exact risk because you know half the numbers are red, half are black and there's also a double zero that's neither red nor black. Easy.
Now let's say you're gaming out the risk of betting on red but there's an unknown number of roulette wheels in the game, each with a variable number of red and black possibilities and your risk depends on an unknown combination of spins of an unknown number of wheels with a unknown number of red and black combinations.
And of course there's the Added Event Risk of Unknown and Infinite possible events that could change all the inputs.
Now, I'm sure you can come up with a computer model of risk for that game. What would it be worth?