vix.ing · top · new · best · stats · spec

How We Tend To Overestimate Powerlaw Tail Exponents

2012/10/06 by Nassim N. Taleb, Taleb, Nassim N.
Economics, Econometrics and Finance · Mathematics · Physics and Astronomy · #Data Analysis #FOS: Economics and business #FOS: Mathematics #FOS: Physical sciences #Risk Management (q-fin.RM) #Statistics Theory (math.ST) #Statistics and Probability (physics.data-an) #math.ST #physics.data-an #q-fin.RM #stat.TH

paper · pdf · doi:10.48550/arxiv.1210.1966

arxiv created 2012/10/06 · arxiv updated 2012/10/09

Abstract

In the presence of a layer of metaprobabilities (from uncertainty concerning the parameters), the asymptotic tail exponent corresponds to the lowest possible tail exponent regardless of its probability. The problem explains "Black Swan" effects, i.e., why measurements tend to chronically underestimate tail contributions, rather than merely deliver imprecise but unbiased estimates.

Related