"We were seeing 25-sigma events, several days in a row.” Goldman Sachs' CFO David Viniar""We were seeing 25-sigma events, several days in a row.” Goldman Sachs' CFO David Viniar"
Every time I see somebody talking about some grand financial event constituting an x-sigma event, I shake my head in disbelief: what a clown. Last few weeks on Bitcoin twitter was no exception, since what bitcoin did was SOOO CRAZY REVOLUTIONARY as to warrant the 4-5-8-sigma construction. (And often using that statement to suggest there was market manipulation because it's not "normal".)
ASIDE: Lol, there's an entire journal article outlining how ridiculous 25-sigma is, conclusion: VEEERY)
uhm, 100,000 years sounds low. Indeed, Dowd and colleagues start doing some math:
this is a period (considerably) longer than the entire period that has elapsed since Big Bang. If we observe a profit or loss once a day, then a mere 8-sigma event should occur less than once in the entire history of the universe.
...and they're only at 8.
a 20-event corresponds to an expected occurrence period
measured in years that is 10 times larger than the higher of the estimates of the
number of particles in the Universe. For its part, a 25-sigma event corresponds to an
expected occurrence period that is equal to the higher of these estimates but with the
decimal point moved 52 places to the left!
"Funny things these 25-sigma events. And surprisingly common too. ""Funny things these 25-sigma events. And surprisingly common too. "
Anyway, here's our beloved Nassim Taleb (REMEMBER HIM?!) echoing what I think basically every time somebody gives me a "uh, look, what just happened was an x-sigma event" -- from _Statistical Consequences of Fat Tails_, a book I had the occasion to look into today
If there is a tiny probability, <10^−10 that the data might not be Gaussian, one can firmly reject Gaussianity in favor of the thick-tailed distribution
Financial markets don't do normal distributions.
BACKGROUND:
(MIT explanation: https://news.mit.edu/2012/explained-sigma-0209)
Whenever people talk like that it tells me they have a financial mathematics education without actually understanding financial mathematics.
they have the vocab and the cred, just not the competence
probably 95% of the leaders in banking
It's too bad taleb is no longer open to Bitcoin. I really enjoyed Fooled by Randomness.
same. Still do.
As a matter of fact, I should go back and read it. Would be a nice series for book reviews... goddamnit I already HAVE book review series on SN!