Skip to main content

On the Shadow Moments of Apparently Infinite-Mean Phenomena

Part of the Springer Proceedings in Complexity book series (SPCOM)

Abstract

We propose an approach to compute the conditional moments of fat-tailed phenomena that, only looking at data, could be mistakenly considered as having infinite mean. This type of problems manifests itself when a random variable Y has a heavy-tailed distribution with an extremely wide yet bounded support.

We introduce the concept of dual distribution, by means of a logarithmic transformation that smoothly removes the upper bound. The tail of the dual distribution can then be studied using extreme value theory, without making excessive parametric assumptions, and the estimates one obtains can be used to study the original distribution and compute its moments by reverting the transformation.

The central difference between our approach and a simple truncation is in the smoothness of the transformation between the original and the dual distribution, allowing use of extreme value theory.

Keywords

  • Power laws
  • Complex networks
  • Econophysics

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-319-96661-8_16
  • Chapter length: 10 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   169.00
Price excludes VAT (USA)
  • ISBN: 978-3-319-96661-8
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   219.99
Price excludes VAT (USA)
Hardcover Book
USD   249.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.

Notes

  1. 1.

    Note that treating Y as belonging to the Fréchet class is a mistake. If a random variable has a finite upper bound, it cannot belong to the Fréchet class, but rather to the Weibull class [2].

  2. 2.

    Note that we require that the upper bound H be both finite and known –as with the world’s population or the capital of a bank. In case H is not known, we fail to see the difference with an unbounded random variable.

  3. 3.

    Note that the use of logarithmic transformation is quite natural in the context of utility.

  4. 4.

    There are alternative methods to face finite (or concave) upper bounds, i.e., the use of tempered power laws (with exponential dampening) [7] or stretched exponentials [8]; while being of the same nature as our exercise, these methods do not allow for immediate applications of extreme value theory or similar methods for parametrization.

  5. 5.

    We call it “shadow”, as it is not immediately visible from the data.

  6. 6.

    Remember that for a GPD random variable Z, \(E\left[ Z^ p\right] <\infty \) iff \(\xi < 1/p\).

  7. 7.

    Because of the similarities between \(1-F(y)\) and \(1-G(z)\), at least up until M, the GPD approximation will give two statistically undistinguishable estimates of \(\xi \) for both tails [3].

References

  1. Beirlant, J., Alves, I.F., Gomes, I., Meerschaert, M.: Extreme value statistics for truncated Pareto-type distributions (2014). arXiv preprint: arXiv:1410.4097

  2. de Haan, L., Ferreira, A.: Extreme Value Theory: An Introduction. Springer, New York (2006)

    CrossRef  Google Scholar 

  3. Embrechts, P., Klüppelberg, C., Mikosch, T.: Modelling Extremal Events. Springer, Heidelberg (2003)

    MATH  Google Scholar 

  4. Falk, M., Hüsler, J., Reiss, R.-D.: Laws of Small Numbers: Extremes and Rare Events. Birkhäuser, Basel (2004)

    CrossRef  Google Scholar 

  5. Inmaculada, B.A., Meerschaert, M.M., Panorska, A.K.: Parameter estimation for the truncated Pareto distribution. J. Am. Stat. Assoc. 101, 270–277 (2006)

    MathSciNet  CrossRef  Google Scholar 

  6. Maronna, R., Martin, R.D., Yohai, V.: Robust Statistics - Theory and Methods. Wiley, New York (2006)

    CrossRef  Google Scholar 

  7. Rachev, S.T., Kim, Y.S., Bianchi, M.L., Fabozzi, F.J.: Financial Models with Lévy Processes and Volatility Clustering. Wiley, Hoboken (2011)

    CrossRef  Google Scholar 

  8. Laherrere, J., Sornette, D.: Stretched exponential distributions in nature and economy: “fat tails” with characteristic scales. Eur. Phys. J. B Condens. Matter Complex Syst. 2(4), 525–539 (1998)

    CrossRef  Google Scholar 

  9. Sprenkle, C.: Warrant prices as indicators of expectations and preferences. Yale Econ. Essays 1, 179–231 (1961)

    Google Scholar 

  10. Taleb, N.N.: Incerto Technical Companion. The Statistical Consequences of Fat Tails, vol. 1 (2018). www.fooledbyrandomness.com

  11. Einmahl, J., Einmahl, J., de Haan, L.: Limits to Human Life Span Through Extreme Value Theory. Center Discussion Paper Series No. 2017-051. CentER, Center for Economic Research, Tilburg (2017)

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Nassim Nicholas Taleb .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2018 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Taleb, N.N., Cirillo, P. (2018). On the Shadow Moments of Apparently Infinite-Mean Phenomena. In: Morales, A., Gershenson, C., Braha, D., Minai, A., Bar-Yam, Y. (eds) Unifying Themes in Complex Systems IX. ICCS 2018. Springer Proceedings in Complexity. Springer, Cham. https://doi.org/10.1007/978-3-319-96661-8_16

Download citation