Bayesian uncertainty management in temporal dependence of extremes

Extremes volume 19, pages491–515(2016)Cite this article

Abstract

Both marginal and dependence features must be described when modelling the extremes of a stationary time series. There are standard approaches to marginal modelling, but long- and short-range dependence of extremes may both appear. In applications, an assumption of long-range independence often seems reasonable, but short-range dependence, i.e., the clustering of extremes, needs attention. The extremal index 0 < 𝜃 ≀ 1 is a natural limiting measure of clustering, but for wide classes of dependent processes, including all stationary Gaussian processes, it cannot distinguish dependent processes from independent processes with 𝜃 = 1. Eastoe and Tawn (Biometrika 99, 43–55 2012) exploit methods from multivariate extremes to treat the subasymptotic extremal dependence structure of stationary time series, covering both 0 < 𝜃 < 1 and 𝜃 = 1, through the introduction of a threshold-based extremal index. Inference for their dependence models uses an inefficient stepwise procedure that has various weaknesses and has no reliable assessment of uncertainty. We overcome these issues using a Bayesian semiparametric approach. Simulations and the analysis of a UK daily river flow time series show that the new approach provides improved efficiency for estimating properties of functionals of clusters.

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

References

  1. Asadi, P., Davison, A.C., Engelke, S.: Extremes on river networks. Ann. Appl. Stat. 9, 2023–2050 (2015)

    MathSciNet  Article  MATH  Google Scholar 

  2. Ballani, F., Schlather, M.: A construction principle for multivariate extreme value distributions. Biometrika 98, 633–645 (2011)

    MathSciNet  Article  MATH  Google Scholar 

  3. de Carvalho, M., Ramos, A.: Bivariate extreme statistics, II. Revstat 10, 83–107 (2012)

    MathSciNet  MATH  Google Scholar 

  4. Cheng, L., Gilleland, E., Heaton, M.J., AghaKouchak, A.: Empirical Bayes estimation for the conditional extreme value model. Stat. 3, 391–406 (2014)

    Article  Google Scholar 

  5. Coles, S.: An introduction to statistical modeling of extreme values. Springer, London (2001)

    Google Scholar 

  6. Coles, S.G., Pauli, F.: Models and inference for uncertainty in extremal dependence. Biometrika 89, 183–196 (2002)

    MathSciNet  Article  MATH  Google Scholar 

  7. Coles, S.G., Tawn, J.A.: Statistical methods for multivariate extremes: an application to structural design (with discussion). J. R. Stat. Soc. Ser. C 43, 1–48 (1994)

    MATH  Google Scholar 

  8. Connor, R.J., Mosimann, J.E.: Concepts of independence for proportions with a generalization of the Dirichlet distribution. J. Am. Stat. Assoc. 64, 194–206 (1969)

    MathSciNet  Article  MATH  Google Scholar 

  9. Cooley, D., Davis, R.A., Naveau, P.: The pairwise beta distribution: a flexible parametric multivariate model for extremes. J. Multivar. Anal. 101, 2103–2117 (2010)

    MathSciNet  Article  MATH  Google Scholar 

  10. Das, B., Resnick, S.I.: Conditioning on an extreme component: model consistency with regular variation on cones. Bernoulli 17, 226–252 (2011)

    MathSciNet  Article  MATH  Google Scholar 

  11. Davis, R.A., Mikosh, T.: The extremogram: a correlogram for extreme events. Bernoulli 15, 977–1009 (2009)

    MathSciNet  Article  MATH  Google Scholar 

  12. Davison, A.C., Smith, R.L.: Models for exceedances over high thresholds (with discussion). J. R. Stat. Soc. Ser. B 52, 393–442 (1990)

    MathSciNet  MATH  Google Scholar 

  13. Eastoe, E.F., Tawn, J.A.: Modelling the distribution of the cluster maxima of exceedances of subasymptotic thresholds. Biometrika 99, 43–55 (2012)

  14. Einmahl, J.H.J., de Haan, L., Piterbarg, V.I.: Nonparametric estimation of the spectral measure of an estreme value distribution. Ann. Stat. 29, 1401–1423 (2001)

    MathSciNet  Article  MATH  Google Scholar 

  15. Einmahl, J.H.J., Segers, J.: Maximum empirical likelihood estimation of the spectral measure of an extreme-value distribution. Ann. Stat. 37, 2953–2989 (2009)

    MathSciNet  Article  MATH  Google Scholar 

  16. Fawcett, L., Walshaw, D.: A hierarchical model for extreme wind speeds. J. R. Stat. Soc. Ser. C 55, 631–646 (2006)

    MathSciNet  Article  MATH  Google Scholar 

  17. Fawcett, L., Walshaw, D.: Improved estimation for temporally clustered extremes. Environmetrics 18, 173–188 (2007)

    MathSciNet  Article  Google Scholar 

  18. Ferguson, T.S.: A Bayesian analysis of some nonparametric problems. Ann. Stat. 1, 209–230 (1973)

    MathSciNet  Article  MATH  Google Scholar 

  19. Ferro, C.A.T., Segers, J.: Inference for clusters of extreme values. J. R. Stat. Soc. Ser. B 65, 545–556 (2003)

    MathSciNet  Article  MATH  Google Scholar 

  20. Genest, C., Ghoudi, K., Rivest, L.-P.: A semiparametric estimation procedure of dependence parameters in multivariate families of distributions. Biometrika 82, 543–552 (1995)

    MathSciNet  Article  MATH  Google Scholar 

  21. Genz, A., Bretz, F.: Computation of multivariate normal and t probabilities lecture notes in statistics. Springer, Heidelberg (2009)

    Google Scholar 

  22. Genz, A., Bretz, F., Miwa, T., Mi, X., Leisch, F., Scheipl, F., Hothorn, T.: mvtnorm: multivariate normal and t distributions. R package version 1.0-2 (2014)

  23. Green, P.J.: Reversible jump Markov chain Monte Carlo computation and Bayesian model determination. Biometrika 82, 711–732 (1995)

    MathSciNet  Article  MATH  Google Scholar 

  24. de Haan, L., de Ronde, J.: Sea and wind: multivariate extremes at work. Extremes 1, 7–45 (1998)

    MathSciNet  Article  MATH  Google Scholar 

  25. Hall, P., Tadjvidi, N.: Distribution and dependence-function estimation for bivariate extreme-value distributions. Bernoulli 6, 835–844 (2000)

    MathSciNet  Article  MATH  Google Scholar 

  26. Heffernan, J.E., Resnick, S.I.: Limit laws for random vectors with an extreme component. Ann. Appl. Probab. 17, 537–571 (2007)

    MathSciNet  Article  MATH  Google Scholar 

  27. Heffernan, J.E., Tawn, J.A.: A conditional approach for multivariate extreme values (with discussion). J. R. Stat. Soc. Ser. B 66, 497–546 (2004)

    MathSciNet  Article  MATH  Google Scholar 

  28. Hjort, N.L., Holmes, C., MĂŒller, P., Walker, S.G.: Bayesian Nonparametrics. Cambridge University Press, New York (2010)

    Google Scholar 

  29. Hsing, T., HĂŒsler, J., Leadbetter, M.R.: On the exceedance point process for a stationary sequence. Probab. Theory Relat. Fields 78, 97–112 (1988)

    MathSciNet  Article  MATH  Google Scholar 

  30. Hyndman, R.J.: Computing and graphing highest density regions. Am. Stat. 50, 120–126 (1996)

    Google Scholar 

  31. Ishwaran, H., James, L.F.: Gibbs sampling methods for stick-breaking priors. J. Am. Stat. Assoc. 96, 161–172 (2001)

    MathSciNet  Article  MATH  Google Scholar 

  32. Ishwaran, H., James, L.F.: Approximate Dirichlet process computing in finite normal mixtures: smoothing and prior information. J. Comput. Graph. Stat. 11, 508–532 (2002)

    MathSciNet  Article  Google Scholar 

  33. Ishwaran, H., Zarepour, M.: Markov chain Monte Carlo in approximate Dirichlet and beta two-parameter process hierarchical models. Biometrika 87, 371–390 (2000)

    MathSciNet  Article  MATH  Google Scholar 

  34. Keef, C., Papastathopoulos, I., Tawn, J.A.: Estimation of the conditional distribution of a multivariate variable given that one of its components is large: additional constraints for the Heffernan and Tawn model. J. Multivar. Anal. 115, 396–404 (2013)

    MathSciNet  Article  MATH  Google Scholar 

  35. Keef, C., Tawn, J., Svensson, C.: Spatial risk assesment for extreme river flows. J. R. Stat. Soc. Ser. C 58, 601–618 (2009)

    MathSciNet  Article  Google Scholar 

  36. Kotz, S., Nadarajah, S.: Extreme value distributions: theory and applications. Imperial College Press, London (2000)

    Google Scholar 

  37. Kratz, M.F., RootzĂ©n, H.: On the rate of convergence for extremes of mean square differentiable stationary normal processes. J. Appl. Probab. 34, 908–923 (1997)

    MathSciNet  Article  MATH  Google Scholar 

  38. Kulik, R., Soulier, P.: Heavy tailed time series with extremal independence. Extremes 18, 273–299 (2015)

    MathSciNet  Article  MATH  Google Scholar 

  39. Leadbetter, M.R.: Extremes and local dependence in stationary sequences. Probab. Theory Relat. Fields 65, 291–306 (1983)

    MathSciNet  MATH  Google Scholar 

  40. Leadbetter, M.R., Lindgren, G., Rootzén, H.: Extremes and related propoperties of random sequences and processes. Springer, New York (1983)

    Google Scholar 

  41. Ledford, A.W., Tawn, J.A.: Statistics for near independence in multivariate extreme values. Biometrika 83, 169–187 (1996)

    MathSciNet  Article  MATH  Google Scholar 

  42. Ledford, A.W., Tawn, J.A.: Diagnostics for dependence within time series extremes. J. R. Stat. Soc. Ser. B 65, 521–543 (2003)

    MathSciNet  Article  MATH  Google Scholar 

  43. Marron, J.S., Wand, M.P.: Exact mean integrated squared error. Ann. Stat. 20, 712–736 (1992)

    MathSciNet  Article  MATH  Google Scholar 

  44. Mitra, A., Resnick, S.I.: Modeling multiple risks: hidden domain of attraction. Extremes 16, 507–538 (2013)

    MathSciNet  Article  MATH  Google Scholar 

  45. O’Brien, G.L.: Extreme values for stationary and Markov sequences. Ann. Probab. 15, 281–291 (1987)

    MathSciNet  Article  MATH  Google Scholar 

  46. Papaspiliopoulos, O., Roberts, G.O.: Retrospective Markov chain Monte Carlo methods for Dirichlet process hierarchical models. Biometrika 95, 169–186 (2008)

    MathSciNet  Article  MATH  Google Scholar 

  47. Papastathopoulos, I., Strokorb, K., Tawn, J.A., Butler, A.: Extreme events of Markov chains. To appear (2016)

  48. Peng, L., Qi, Y.: Discussion of “A conditional approach for multivariate extreme values”, by J.E. Heffernan and J.A. Tawn. J. R. Stat. Soc. Ser. B 66, 541–542 (2004)

    Google Scholar 

  49. Poon, S.-H., Rockinger, M., Tawn, J.A.: Modelling extreme-value dependence in international stock markets. Stat. Sin. 13, 929–953 (2003)

    MathSciNet  MATH  Google Scholar 

  50. Porteus, I., Ihler, A., Smyth, P., Welling, M.: Gibbs sampling for (coupled) infinite mixture models in the stick breaking representation. In: Proceedings of the 22nd Annual Conference on Uncertainty in Artificial Intelligence (2006)

  51. Reich, B.J., Shaby, B.A., Cooley, D.: A hierarchical model for serially-dependent extremes: a study of heat waves in the Western US. J. Agric. Biol. Environ. Stat. 19, 119–135 (2014)

    MathSciNet  Article  MATH  Google Scholar 

  52. Robert, C.Y.: Automatic declustering of rare events. Biometrika 100, 587–606 (2013)

    MathSciNet  Article  MATH  Google Scholar 

  53. Roberts, G.O., Rosenthal, J.S.: Examples of adaptive MCMC. J. Comput. Graph. Stat. 18, 349–367 (2009)

    MathSciNet  Article  Google Scholar 

  54. Segers, J.: Functionals of clusters of extremes. Adv. Appl. Probab. 35, 1028–1045 (2003)

    MathSciNet  Article  MATH  Google Scholar 

  55. Sethuraman, J.: A constructive definition of Dirichlet priors. Stat. Sin. 4, 639–650 (1994)

    MathSciNet  MATH  Google Scholar 

  56. Smith, R.L., Tawn, J.A., Coles, S.G.: Markov chain models for threshold exceedances. Biometrika 84, 249–268 (1997a)

    MathSciNet  Article  MATH  Google Scholar 

  57. Smith, R.L., Tawn, J.A., Coles, S.G.: Markov chain models for threshold exceedances. Biometrika 84, 249–268 (1997b)

    MathSciNet  Article  MATH  Google Scholar 

  58. Smith, R.L., Weissman, I.: Estimating the extremal index. J. R. Stat. Soc. Ser. B 56, 515–528 (1994)

    MathSciNet  MATH  Google Scholar 

  59. SĂŒveges, M.: Likelihood estimation of the extremal index. Extremes 10, 41–55 (2007)

    MathSciNet  Article  MATH  Google Scholar 

  60. SĂŒveges, M., Davison, A.C.: A case study of a “Dragon-King”: the 1999 Venezuelan catastrophe. Eur. Phys. J. Spec. Top. 205, 131–146 (2012)

    Article  Google Scholar 

  61. Winter, H.C., Tawn, J.A.: Modelling heatwaves in central France: a case study in extremal dependence. J. R. Stat. Soc. Ser. C 65, 345–365 (2016)

    Article  Google Scholar 

Download references

Author information

Affiliations

  1. EPFL-FSB-MATHAA-STAT, Ecole Polytechnique Fédérale de Lausanne, Station 8, 1015, Lausanne, Switzerland

    T. Lugrin & A. C. Davison

  2. Department of Mathematics and Statistics, Lancaster University, Lancaster, LA1 4YF, UK

    J. A. Tawn

Authors
  1. T. Lugrin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. A. C. Davison
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. J. A. Tawn
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to T. Lugrin.

Additional information

This research was partially supported by the Swiss National Science Foundation.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Lugrin, T., Davison, A.C. & Tawn, J.A. Bayesian uncertainty management in temporal dependence of extremes. Extremes 19, 491–515 (2016). https://doi.org/10.1007/s10687-016-0258-0

Download citation

Keywords

  • Asymptotic independence
  • Bayesian semiparametrics
  • Conditional extremes
  • Dirichlet process
  • Extreme value theory
  • Extremogram
  • Risk analysis
  • Threshold-based extremal index

AMS 2000 Subject Classifications

  • 62G32
  • 62P12