The genetics of twin studies have a bias showing more heredity than in reality, owing to a statistical artifact. The twin studies for heredity are based on comparing the correlation between 2 identical twins minus that between 2 fraternal ones (assumed to be sharing half their genes). The use of fraternal twins as control is assumed to extract the “environmental” factors. Problem: Correlation is conditional and psychologists think it is unconditional. We show how the math is entirely different. The core error is that genes and environment are not separable and additive.
A first, very introductory presentation of fragility as linked to both nonlinearity and dislike of variations. Antifragility is almost the opposite, limited to a specific range of variations.
- Why everything fragile must be concave.
- The medical S curve.
- Why harm to the climate is necessarily nonlinear in dose response.
- How hospitals can be overcrowded unless there are redundancies.
Further discussions will be more technical.
Modern financial theory assumes that distributions are elliptical. We show what happens if the assumption doesn’t hold. And the assumption doesn’t hold.
Diversification does NOT reduce risks in the financial market; it causes near-certain long term blowups under any leverage.
For n observations, what is the hidden moment? What are you missing from the “empirical” distribution?
Say the maximum flood was 3 meters or maximum loss was 22%. What are we missing in the statistical properties?
Link to the Paper mentioned in the video – What You See and What You Don’t See: The Hidden Moments of a Probability Distribution
A simple tutorial explaining how in the presence of power laws (with low exponent) most of the body of the distribution becomes noise. Once you establish that a variable is in the power-law class, some necessary consequences come out. To debunk that history is dominated by tail events, you must show it does not follow a power law.
Note: If viewing this as an email please click through to the post to view content.
Antifragile explains why understanding x is different from f(x) the payoff or exposure from x. Most of the harm/gains come from f(x) being convex or concave not understanding x. Forecasting is off an average, and average is for academics and other morons.
This video illustrates the point with XIV that went bust while being correct about volatility –and why people who make money are usually wrong.
Pourquoi devrait-on cesser d’écouter ceux qui parlent au lieu d’agir ? Pourquoi les entreprises font-elles faillite ? Comment se fait-il que nous avons plus d’esclaves aujourd’hui qu’au temps des Romains ? Pourquoi imposer la démocratie aux autres pays ne marche jamais ?
Réponse : trop nombreux sont ceux qui dirigent le monde sans mettre leur peau en jeu.
Dans son livre le plus provocateur à ce jour, Taleb donne sa définition et ébranle les nôtres : qu’est-ce que comprendre le monde, réussir sa vie professionnelle, contribuer à une société juste ou injuste, détecter les non-sens et influencer les autres ?
D’Hammourabi à Sénèque, du géant Antée à Donald Trump, de Kant à Gros Tony, Taleb choisit ses exemples et montre qu’avoir quelque chose à perdre, vouloir accepter le risque, y voir une question de justice, d’honneur et de sacrifice, est pour les héros, les saints et bon nombre d’êtres humains épanouis… une essentielle règle du jeu.
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”.
So I am fed up with academics who say “we know it is fat tails” yet not understand the consequences.
This tutorial presents the intuitions of the randomness of sample correlation (spurious correlation) and the methodologies in derivations. Some later sections are somewhat technical as Nassim rederived an old equation with more precise functions (in order to apply to fat tails) and showed the distribution of the maximum of d variables with n points per variable.
This paves the way to the real scientific work on random matric theory under fat tails and the failure of Marchenko-Pastur.