Again, the failure of financial risk models in 2008 was pretty much the same thing. Same techniques, similar failures.
-
-
Replying to @anomalyuk @fxxfy
Isn't there a Moldbug post about all this?
2 replies 1 retweet 0 likes -
Moldbug wrote about central banking & maturity transformation, not details of risk management. NNT's the main guy
3 replies 0 retweets 3 likes -
1 reply 0 retweets 0 likes
-
probabilistic modelling uses assumptions about correlations. Correlations are moved by factors not in the model.
1 reply 0 retweets 0 likes -
Shocking part with reading about risk models and VaR was the basic assumption of the normal distribution!!
1 reply 0 retweets 0 likes -
well, Central Limit Theorem and all that, not so bad. You supplement VaR with stress scenarios for extremes
2 replies 0 retweets 0 likes -
Well that's the central point of Taleb - you can't model a fat-tailed, power-law domain with bell curve.
1 reply 1 retweet 0 likes -
Replying to @i_contemplate_ @anomalyuk and
And even the smartest ppl were doing it. https://en.wikipedia.org/wiki/David_X._Li#CDOs_and_Gaussian_copula …
1 reply 0 retweets 0 likes -
A big issue is that if you give a trader a VaR "budget", he'll seek out fat tails.
1 reply 0 retweets 0 likes
it's risk he's getting paid for taking, but his controllers aren't seeing. Goodhart's Law.
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.