The Black Swan: The Impact of the Highly Improbable · chapter 7 · id the-black-swan-c7-01-the-gaussian-bell-curve-is-rou
“The Gaussian bell curve is routinely misapplied to domains where it does not belong -- financial returns, city sizes, book sales, wealth distribution. This misapplication is 'the great intellectual fraud' and has caused catastrophic financial losses.”
TRUE, BUTconfidence: high⚠ extracted by pipeline, re-audit pending
Receipts
Cont (2001), 'Empirical Properties of Asset Returns', Quantitative FinanceFLAGGED: DOI not in registry
Daily stock returns exhibit excess kurtosis of 5-50 (Gaussian = 3), meaning extreme events occur 10-100x more frequently than a normal distribution predicts.
Mandelbrot (2001), 'Scaling in Financial Prices: Tails and Dependence', Yale Mathematicscheck errored · retry queued
Cotton price data from 1900-1960 shows fat tails inconsistent with Gaussian distribution. Price changes follow a stable Levy distribution with tail exponent around 1.7.
Aldous (2007), Review of The Black Swan, UC Berkeley Statisticssource alive
Taleb is sensible (going on prescient) in his discussion of financial markets but tends toward irrelevant or ridiculous exaggeration otherwise. The Gaussian is not 'fraudulent' in domains where it demonstrably works (measurement error, heights, blood pressure).
Clauset, Shalizi & Newman (2009), SIAM ReviewDOI registry: valid
Of 24 purported power-law datasets tested rigorously, only 7 survived statistical tests. Many 'Extremistan' phenomena may not follow clean power laws either.
This claim is a stable, citable object. If you can falsify a verdict, tell us. Corrections are loud here.