Skip to main content
SpringerLink
Log in

On the Use of Feed-Forward Neural Networks to Discriminate between Models in Financial and Insurance Risk Frameworks

  • Conference paper
Knowlege-Based and Intelligent Information and Engineering Systems (KES 2011)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 6882))

  • 1290 Accesses

Abstract

The problem of assessing if a sample is coming from one of two probability distributions is most likely one of the oldest problems in the field of testing statistical hypotheses and a number of papers has been produced over the years without finding a most powerful test for this goal. In financial and insurance risk modeling, this problem is often addressed to identify the best extreme values model in a battery of alternatives or to design the heaviness of the tail of the underlying distribution. Taking advantage of the well known performance in classificatory problems of neural networks, the use of feed-forward neural networks for discrimination between two distributions is herein proposed and the power of a neural goodness-of-fit test is estimated for small, moderate and large sample sizes in a wide range of symmetric and skewed alternatives. The empirical power of the procedure described is compared to the power of eight classic and well known normality tests for a sample to come from a normal distribution against each of twelve close-to normal alternatives. The neural test resulted to be the most powerful in the whole battery and its behavior was consistent with the expected statistical properties.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Adcock, C.J.: Asset pricing and portfolio selection based on the multivariate extended skew-Student-t distribution. Annals of Operations Research 176(1), 221–234 (2010)

    Article  MathSciNet  MATH  Google Scholar 

  2. Anderson, T.W., Darling, D.A.: A test of goodness of fit –. Journal of the American Statistical Association 49, 765–769 (1954)

    Article  MathSciNet  MATH  Google Scholar 

  3. Bain, L.J., Engelhardt, M.: Probability of correct selection of Weibull versus gamma based on likelihood ratio. Communication in Statistics: Theory and Methods 9, 375–381 (1980)

    Article  MATH  Google Scholar 

  4. Bishop, C.M.: Neural Networks for pattern recognition. Oxford University Press, Oxford (1985)

    MATH  Google Scholar 

  5. Campbell, R., Huisman, R., Koedijk, K.: Optimal portfolio selection in a Value-at-Risk framework. Journal of Banking & Finance 25(9), 1789–1804 (2001)

    Article  Google Scholar 

  6. Chernoff, H.: A Measure of Asymptotic Efficiency for Tests of a Hypothesis based on the Sum of Observations. Annals of Mathematical Statistics 23, 493–507 (1952)

    Article  MathSciNet  MATH  Google Scholar 

  7. Cox, D.R.: Tests of separate families of hypotheses. In: Proceedings of the Fourth Berkeley Symposium in Mathematical Statistics and Probability, pp. 105–123. University of California Press, Berkeley (1961)

    Google Scholar 

  8. Cox, D.R.: Further results on tests of separate families of hypotheses. Journal of Royal Statistical Society 24, 406–424 (1962)

    MathSciNet  MATH  Google Scholar 

  9. Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines and other kernel-based learning methods. Cambridge University Press, Cambridge (2000)

    Book  MATH  Google Scholar 

  10. D’Agostino, R.B.: An omnibus test for normality for moderate and large size samples. Biometrika 58(2), 341–348 (1971)

    Article  MathSciNet  MATH  Google Scholar 

  11. D’Agostino, R.B., Stephens, M.A.: Goodness-of-fit techniques. Marcel Dekker, New York (1986)

    MATH  Google Scholar 

  12. Dey, A.K., Kundu, D.: Discriminating Among the Log-Normal, Weibull, and Generalized Exponential Distributions. IEEE Transactions on reliability 58(3), 416–424 (2009)

    Article  Google Scholar 

  13. Dumonceaux, R., Antle, C.E.: Discrimination between the lognormal and the Weibull distributions. Technometrics 15(4), 923–926 (1973)

    Article  MATH  Google Scholar 

  14. Dumonceaux, R., Antle, C.E., Haas, G.: Likelihood ratio test for discrimination between two models with unknown location and scale parameters. Technometrics 15(1), 19–27 (1973)

    MathSciNet  MATH  Google Scholar 

  15. Filliben, J.R.: The probability plot correlation coefficient test for normality. Technometrics 17, 111–117 (1975)

    Article  MATH  Google Scholar 

  16. Frosini, B.: Distribution and power of a new goodness of fit statistic. Statistica 3, 389–413 (1983)

    MathSciNet  Google Scholar 

  17. Gordy, M.B.: A comparative anatomy of credit risk models. Journal of Banking & Finance 24(1-2), 119–149 (2000)

    Article  Google Scholar 

  18. Han, T.S., Kobayashi, K.: The strong converse theorem for hypothesis testing. IEEE Transactions on Information Theory 35, 178–180 (1989)

    Article  MathSciNet  MATH  Google Scholar 

  19. Heyde, C., Khanhav, A.: On the Problem of Discriminating between the Tails of Distributions. In: Contributions to Probability and Statistics: Applications and Challenges, Proceedings of the International Statistics Workshop, University of Canberra, April 4 - 5, pp. 246–258 (2005)

    Google Scholar 

  20. Hoeffding, W.: Asymptotically optimal test for multinomial distributions. Annals of Mathematical Statistics 36, 369–401 (1965)

    Article  MathSciNet  MATH  Google Scholar 

  21. Hornik, K.: Approximation capabilities of multilayer feedforward networks. Neural Networks 4, 251–257 (1991)

    Article  Google Scholar 

  22. Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Networks 2, 359–366 (1989)

    Article  Google Scholar 

  23. Kappenman, R.F.: On a method for selecting a distributional model. Communication in Statistics: Theory and Methods 11, 663–672 (1982)

    Article  Google Scholar 

  24. Kappenman, R.F.: A simple method for choosing between the lognormal and Weibull models. Statistics & Probability Letters 7, 123–126 (1989)

    Article  MathSciNet  Google Scholar 

  25. Landry, L., Leparge, Y.: Empirical behavior of some tests for normality. Communications in Statistics: Simulation and Computation 21, 971–999 (1992)

    Article  Google Scholar 

  26. Lehman, E.L., Romano, J.P.: Testing Statistical Hypotheses. Springer, Heidelberg (2005)

    Google Scholar 

  27. Levenberg, K.: A Method for the Solution of Certain Non-Linear Problems in Least Squares. The Quarterly of Applied Mathematics 2, 164–168 (1944)

    Article  MathSciNet  MATH  Google Scholar 

  28. Longin, F.: The choice of the distribution of asset returns: How extreme value theory can help? Journal of Banking & Finance 29(4), 1017–1035 (2005)

    Article  Google Scholar 

  29. Marquardt, D.: An Algorithm for Least-Squares Estimation of Nonlinear Parameters. SIAM Journal on Applied Mathematics 11(2), 431–441 (1963)

    Article  MathSciNet  MATH  Google Scholar 

  30. Pace, L.: Un test per la verifica dell’ipotesi funzionale complessa con particolare riferimento al controllo della normalità. Rivista di Statistica Applicata 4, 299–308 (1983)

    Google Scholar 

  31. Pakyari, R.: Discriminating between generalized exponential, geometric extreme exponential and Weibull distributions. Journal of statistical computation and simulation 80(12), 1403–1412 (2010)

    Article  MathSciNet  MATH  Google Scholar 

  32. Pesarin, F.: An asymptotically distribution free goodness-of-fit test for statistical distribution depending on two parameters. In: Taillie, C. (ed.) Proc. NATO Adv. Study Inst., Statistical Distributions in Scientific Work, rieste/Italy, vol. 5, pp. 51–56 (1981)

    Google Scholar 

  33. Richard, M.D., Lippmann, R.: Neural network classifiers estimate Bayesian a posteriori probabilities. Neural Computing 3, 461–483 (1991)

    Article  Google Scholar 

  34. Seier, E.: Comparison of tests for univariate normality. Inter-Stat (London) 1, 1–17 (2002)

    Google Scholar 

  35. Shapiro, S.S., Wilk, M.B.: An analysis of variance test for normality (complete samples). Biometrika 52(3-4), 591–611 (1965)

    Article  MathSciNet  MATH  Google Scholar 

  36. Shapiro, S.S., Wilk, M.B., Chen, H.J.: A comparative study of various tests for normality. Journal of the American Statistical Association 63, 1343–1372 (1968)

    Article  MathSciNet  Google Scholar 

  37. Stephens, M.A.: EDF Statistics for goodness of fit and some comparison. Journal of the American Statistical Association 69, 730–737 (1974)

    Article  Google Scholar 

  38. Taroni, G.: Studio comparativo dei test di normalità per alternative prossime alla normale. Statistica applicata 9(2), 231–246 (1997)

    Google Scholar 

  39. Thode Jr., H.C., Smith, L.A., Finch, S.J.: Power of tests of normality for detecting scale contaminated normal samples. Communications in Statistics - Simulation and Computation 12, 675–695 (1983)

    Article  MATH  Google Scholar 

  40. Van der Vaart, A.W.: Asymptotic Statistics. Cambridge Series in Probabilistic Mathematics (1998)

    Google Scholar 

  41. Vasicek, O.: A test for normality based on sample entropy. Journal of the Royal Statistical Society B 38, 54–59 (1976)

    MathSciNet  MATH  Google Scholar 

  42. Watson, G.S.: Goodness of fit tests on a circle. Biometrika 48, 57–63 (1961)

    Article  MathSciNet  MATH  Google Scholar 

  43. White, H.: Maximum likelihood estimation of misspecified models. Econometrica 50(1), 1–25 (1982a)

    Article  MathSciNet  MATH  Google Scholar 

  44. White, H.: Regularity conditions for Cox’s test of non-nested hypotheses. Journal of Econometrics 19, 301–318 (1982b)

    Article  MathSciNet  MATH  Google Scholar 

  45. Zhang, G.P.: Neural Networks for Classification: A Survey. IEEE Transactions on systems, man and cybernetics – Part C: Applications and reviews 30(4), 451–462 (2000)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Dipartimento di Economia e Metodi Quantitativi - Sezione di Statistica, Via Vivaldi, 5, 16100, Genoa, Italy

    Enrico di Bella

Authors
  1. Enrico di Bella
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Institute of Integrated Sensor Systems, University of Kaiserslautern, Erwin-Schroedinger-str. 12, 67663, Kaiserslautern, Germany

    Andreas König

  2. Knowledge-Based Systems Group, Department of Computer Science, University of Kaiserslautern, P.O. Box 3049, 67653, Kaiserslautern, Germany

    Andreas Dengel

  3. School of Business, University of Applied Sciences Northwestern Switzerland, Riggenbachstr. 16, 4600, Olten, Switzerland

    Knut Hinkelmann

  4. Graduate School of Engineering, Osaka Prefecture University, 1-1 Gakuen-cho, 599-8531, Sakai,, Osaka, Japan

    Koichi Kise

  5. KES International, P.O. Box 2115, BN43 9AF, Shoreham-by-sea, UK

    Robert J. Howlett

  6. University of South Australia, Adelaide, 5095, Mawson Lakes, SA, Australia

    Lakhmi C. Jain

Rights and permissions

Reprints and permissions

Copyright information

© 2011 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

di Bella, E. (2011). On the Use of Feed-Forward Neural Networks to Discriminate between Models in Financial and Insurance Risk Frameworks. In: König, A., Dengel, A., Hinkelmann, K., Kise, K., Howlett, R.J., Jain, L.C. (eds) Knowlege-Based and Intelligent Information and Engineering Systems. KES 2011. Lecture Notes in Computer Science(), vol 6882. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23863-5_40

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-23863-5_40

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-23862-8

  • Online ISBN: 978-3-642-23863-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation