The Pareto 80/20 distribution has tail index α = 1.16, so the adjusted tail probability is more than 7 times the naive one.

This is a mathematical claim from Taleb's 2019 work. The claim: the 80/20 Pareto corresponds to α ≈ 1.16, and accounting for parameter uncertainty in α (the 'adjusted' probability) gives a tail probability more than 7 times the naive point estimate in the example given. True: α = log5/log4 ≈ 1.16 is correct, and the calculation in the source (under its stated error in α and threshold) yields a ratio above 7. Mostly true: α is correct and the ratio is about 7, e.g. 6.5–7 under the source's assumptions, or above 7 with a minor arithmetic slip. Mixed: one part is correct (the value of α or a ratio >7) and the other is not. Mostly false: α is right but the ratio is well below 7 (e.g. 2–5) under the stated assumptions. False: both are wrong, or the calculation cannot give the ratio.

Set before the research began.

1. E1 Pareto index - Wikipedia Wikipedia

   “For example, the 80–20 (4:1) rule corresponds to α = log(5)/log(4) ≈ 1.16, 90–10 (9:1) corresponds to α = log(10)/log(9) ≈ 1.05”

2. E2 The 80/20 Rule Is Misnamed. Its Author Said So in 1974. romankalugin.com · 31 August 2026

   “To get an exact 80/20 you need an exponent near 1.16. Nobody has ever attributed that figure to Pareto, because it is not his.”

3. E3 The 80/20 Rule Is Misnamed. Its Author Said So in 1974. romankalugin.com · 31 August 2026

   “To make the top 20 per cent hold exactly 80 per cent, you need α ≈ 1.16. That number appears nowhere in Pareto’s work.”

4. E4 The 80/20 Rule Is Misnamed. Its Author Said So in 1974. romankalugin.com · 31 August 2026

   “Pareto’s own exponent produces a 58/20 rule.”

5. E5 Statistical Consequences of Fat Tails.pdf Scribd (copy of Taleb, Statistical Consequences of Fat Tails) Own record

   “Note that we are operating under the mild case of known probability distributions, as it gets worse under parametric uncertainty.”

6. E6 Fat Tails: Power Laws, Pareto, and Why ML Assumes Thin Tails TheoremPath

   “If wealth follows a Pareto distribution with \(\alpha = 1.16\), then about 80% of total wealth is held by the top 20% of individuals.”

7. E7 How We Tend To Overestimate Powerlaw Tail Exponents Nassim N. Taleb (fooledbyrandomness.com) · October 2012 Own record

   “The asymptotic exponent is the lowest possible one. It does not even require estimation.”

Independent sources confirm the first part of the claim: an 80/20 Pareto split corresponds to α = log5/log4 ≈ 1.16 [E1, E7, E2/E3]. None of the evidence gives the source's calculation of the adjusted tail probability, its assumed error in α, its threshold, or the resulting ratio. E6 says only that the situation gets worse under parametric uncertainty. Without that, the evidence can't show whether the ratio is above 7, so the claim can't be fully resolved under the criteria.