Skip to content

Tag Archives: fat tails

The empirical distribution is … not empirical

Published on Jun 12, 2017 For fat tailed distributions, the empirical distributions does not reflect the true statistical properties, particularly for extremes. This is a simplified side note to a paper with Mark Spitznagel on why people make a mistake by looking at raw historical data as “empiricism”.

Convex Optionality, Fat Tails, Antifragile, Math Puzzle, GMOs, Risk Minds, Smear Campaigns, Eggplant

https://twitter.com/nntaleb/status/678699317947965440 Another piece of advice: only use an office when it is strictly necessary. An office dulls the mind; invites cosmetic & circular work. — NassimNicholasTaleb (@nntaleb) December 20, 2015 My 2015 contribution to the project of creating statistical estimators under Fat Tails. https://t.co/dpAxcsdE8h — NassimNicholasTaleb (@nntaleb) December 20, 2015 Advice to a kid who […]

Statistics of Violence as Special Case of Fat Tails

A lecture summarizing the paper on violence with Cirillo to MIT and NECSI data scientists, mostly explaining to data scientists how to work with fat tails and only indirectly addressing Pinker by responding to those fooled by the illusion of drop in violence:     Uploaded on Jul 10, 2015 A lunch discussion at MIT […]

The Law of Large Numbers and Fat Tailed Distributions

A general presentation of my research. In which I debunk some BS in social science (which includes our discussion on violence).

Something people don’t realize about fat-tailed probabilities…

Something people don’t realize about fat-tailed probabilities: We may accept to take risks with .00001 pct chance of blowing up the planet. May be OK for some. But the inconsistency is that we do serially and collectively take A LOT of “one-off” risk. If nothing happens, we may do it again. And again. Or we […]