, Volume 5, Issue 3, pp 219–235 | Cite as

A Dynamic Mixture Model for Unsupervised Tail Estimation without Threshold Selection

  • Arnoldo Frigessi
  • Ola Haug
  • Håvard Rue


Exceedances over high thresholds are often modeled by fitting a generalized Pareto distribution (GPD) on R+. It is difficult to select the threshold, above which the GPD assumption is enough solid and enough data is available for inference. We suggest a new dynamically weighted mixture model, where one term of the mixture is the GPD, and the other is a light-tailed density distribution. The weight function varies on R+ in such a way that for large values the GPD component is predominant and thus takes the role of threshold selection. The full data set is used for inference on the parameters present in the two component distributions and in the weight function. Maximum likelihood provides estimates with approximate standard deviations. Our approach has been successfully applied to simulated data and to the (previously studied) Danish fire loss data set. We compare the new dynamic mixture method to Dupuis' robust thresholding approach in peaks-over-threshold inference. We discuss robustness with respect to the choice of the light-tailed component and the form of the weight function. We present encouraging simulation results that indicate that the new approach can be useful in unsupervised tail estimation, especially in heavy tailed situations and for small percentiles.

peaks over threshold Danish fire loss data shape parameter heavy tailed distribution maximum likelihood mixture models 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Balkema, A.A. and de Haan, L., “Residual life time at great age,” Annals of Probability 2, 792–804, (1974).Google Scholar
  2. Crovella, M. and Taqqu, M., “Estimating the heavy tail index from scaling properties,” Methodology and Computing in Applied Probability 1, 55–79, (1999).Google Scholar
  3. Davison, A.C. and Smith, R.L., “Models for exceedances over high thresholds (with discussion),” Journal of the Royal Statistical Society, Series B 5(3), 393–442, (1990).Google Scholar
  4. Dupuis, D.J., “Exceedances over high thresholds: A guide to threshold selection,” Extremes 1(3), 251–261, (1999).Google Scholar
  5. Embrechts, P., Klüppelberg, C., and Mikosch, T., Modelling Extremal Events, number 33 in Applications of Mathematics: Stochastic Modelling and Applied Probability, Springer Verlag, Heidelberg, 1997.Google Scholar
  6. Feuerverger, A. and Hall, P., “Estimating a tail exponent by modelling departure from a Pareto distribution,” The Annals of Statistics 27(2), 760–781, (1999).Google Scholar
  7. Gilks, W.R., Richardson, S., and Spiegelhalter, D.J., Markov Chain Monte Carlo in Practice, Chapman & Hall, London, 1996.Google Scholar
  8. McNeil, A.J., Estimating the tails of loss severity distributions using extreme value theory, Technical report, Department Mathematik, ETH Zentrum, Zürich.Google Scholar
  9. Meng, X.L. and van Dyk, D., “The em algorithm—an old folk-song sung to a fast new tune (with discussion),” Journal of the Royal Statistical Society, Series B 59(3), 511–567, (1997).Google Scholar
  10. Pickands, J. “Statistical inference using extreme order statistics,” The Annals of Statistics 3, 119–131, (1975).Google Scholar
  11. Resnick, S.I., “Heavy tail modeling and teletraffic data,” The Annals of Statistics 25(5), 1805–1869, (1997).Google Scholar
  12. Robert, C.P. and Casella, G., Monte Carlo Statistical Methods, Springer-Verlag, New York, 1999.Google Scholar
  13. Rootzen, H. and Tajvidi, N., “Extreme value statistics and wind storm losses: A case study,” Scandinavian Actuarial Journal 1, 70–94, (1997).Google Scholar

Copyright information

© Kluwer Academic Publishers 2002

Authors and Affiliations

  • Arnoldo Frigessi
    • 1
    • 2
  • Ola Haug
    • 3
  • Håvard Rue
    • 4
  1. 1.Norwegian Computing CenterOsloNorway, and
  2. 2.University of OsloNorway
  3. 3.Norwegian Computing CenterOsloNorway
  4. 4.Department of Mathematical SciencesThe Norwegian University for Science and TechnologyTrondheimNorway

Personalised recommendations