Scores by kind of claim
Each kind of claim is scored on its own, out of 100: the share that held up, with the range it likely falls in. Fewer resolved claims give a wider range.
-
Factual claims
Statements about the present or the past, checked against the record: did they hold up?
73 67 79 -
Predictions
Statements about events outside the person's control, checked once they fell due: did they come true?
Insufficient record: 0 predictions resolved, 5 needed for a score.
-
Promises
Commitments to the person's or organisation's own future action, with something to deliver: was it delivered?
Insufficient record: 0 promises resolved, 5 needed for a score.
All types combined: 73 (likely 67 to 79, high confidence), from 94 claims: 94 factual claims. It mixes kinds of claim in different proportions for different people, so compare people kind by kind.
Nassim Taleb's claims
48 claims
“On the other hand, CVaR satisfies the coherence bound;”
Nassim Taleb, paper author 2019 On the Statistical Differences between Binary Forecasts and Real World Payoffs (arXiv)
Conditional Value at Risk (CVaR) satisfies the coherence (subadditivity) bound.
Mostly true True in substance, wrong in a detail.
The second judge said resolved true; the verdict shown is the first judge's.
What would count as true or false
Judge against established risk-measure theory. True: the standard literature (for example Artzner et al. 1999, Acerbi & Tasche 2002, Rockafellar & Uryasev) shows that CVaR / expected shortfall, in its standard definition, is a coherent risk measure, and in particular subadditive, for general loss distributions. Mostly true: CVaR is coherent or subadditive only under a standard technical condition (for example continuous distributions, or the properly defined expected shortfall) that the claim does not mention. Mixed: subadditivity holds only for a significant restricted class of distributions. Mostly false: it holds only in narrow special cases. False: the literature shows that CVaR fails subadditivity in general.
Evidence
- Conditional value-at-risk for general loss distributions IDEAS/RePEc (bibliographic record) · 2002
“On the coherence of expected shortfall,”
- Conditional value-at-risk for general loss distributions IDEAS/RePEc (bibliographic record) · 2002
“"Coherent Measures of Risk," Mathematical Finance, Wiley Blackwell, vol. 9(3), pages 203-228, July.”
- On the coherence of expected shortfall | Casualty Actuarial Society Casualty Actuarial Society (abstract of Acerbi & Tasche, Journal of Banking & Finance, 2002) · 2002
“In fact, most definitions of ES lead to the same results when applied to continuous loss distributions. Differences may appear when the underlying loss distributions have discontinuities. In this case even the coherence property of ES can get lost unless one took care of the details in its definition.”
- On the coherence of expected shortfall | Casualty Actuarial Society Casualty Actuarial Society (abstract of Acerbi & Tasche, Journal of Banking & Finance, 2002) · 2002
“We compare some of the definitions of ES, pointing out that there is one which is robust in the sense of yielding a coherent risk measure regardless of the underlying distributions.”
- Bigger Is Not Always Safer: A Critical Analysis of the Subadditivity Assumption for Coherent Risk Measures Risks (MDPI), vol. 7, no. 91, 2019 · 26 August 2019
“They also showed that these conditions are fulfilled for expected shortfall, but not for the traditional value at risk.”
- Bigger Is Not Always Safer: A Critical Analysis of the Subadditivity Assumption for Coherent Risk Measures Risks (MDPI), vol. 7, no. 91, 2019 · 26 August 2019
“Subadditivity of risks does not always apply in reality.”
Reasoning
The Acerbi & Tasche (2002) abstract states that one definition of expected shortfall (ES) is coherent whatever the underlying distribution (E4). It also says that with discontinuous loss distributions, other definitions can lose coherence unless the definition is handled carefully (E3). A 2019 review likewise says the coherence conditions hold for expected shortfall but not for value at risk (E5). CVaR's coherence is therefore well established for the properly defined measure, but the claim does not mention that technical qualification, which matches the criteria's 'mostly true' case.
Cite this claim
Nassim Taleb, “Conditional Value at Risk (CVaR) satisfies the coherence (subadditivity) bound.” (said 2019). Verdict: mostly true. Reliability API, claim c_6584267f89b6, method 0.1.0+28da144b. https://epistacklabs.com/claims/c_6584267f89b6
Claims without a verdict
Is a verdict here wrong, or do you speak for Nassim Taleb? Reply on the claim's own page, with the form at its foot (how replies work). Verdicts are made automatically; how verdicts and scores are made.