Stochastic Environmental Research and Risk Assessment

, Volume 31, Issue 7, pp 1603–1613 | Cite as

Spectral density regression for bivariate extremes

  • Daniela Castro Camilo
  • Miguel de CarvalhoEmail author
Original Paper


We introduce a density regression model for the spectral density of a bivariate extreme value distribution, that allows us to assess how extremal dependence can change over a covariate. Inference is performed through a double kernel estimator, which can be seen as an extension of the Nadaraya–Watson estimator where the usual scalar responses are replaced by mean constrained densities on the unit interval. Numerical experiments with the methods illustrate their resilience in a variety of contexts of practical interest. An extreme temperature dataset is used to illustrate our methods.


Bivariate extremes values Nonstationary extremal dependence structures Spectral density Statistics of extremes 



We thank the editor, associate editor, and reviewers for helpful comments and suggestions on an earlier draft of this article. We extend our thanks to Vanda Inácio de Carvalho, Rodrigo Herrera, Raphael Huser, and Jenny Wadsworth for discussions, and to Edgardo Dörner for computational support. This research was partially supported by the Fondecyt project 11121186.

Supplementary material

477_2016_1257_MOESM1_ESM.pdf (1.2 mb)
Supplementary material 1 (PDF 1258 KB)


  1. Castro D (2015) Bivariate extremes: Modeling, smoothing, and regression. PhD Thesis. Pontificia Universidad Católica de ChileGoogle Scholar
  2. Chavez-Demoulin V, Davison AC (2005) Generalized additive modelling of sample extremes. J R Stat Soc C 54(1):207–222CrossRefGoogle Scholar
  3. Chavez-Demoulin V, Embrechts P, Hofert M (2015) An extreme value approach for modeling operational risk losses depending on covariates. J Risk Insur. doi: 10.1111/jori.12059 Google Scholar
  4. Chen SX (1997) Empirical likelihood-based kernel density estimation. Aust J Stat 39(1):47–56CrossRefGoogle Scholar
  5. Coles SG (2001) An introduction to the statistical modeling of extreme values. Springer, LondonCrossRefGoogle Scholar
  6. Coles SG, Tawn JA (1991) Modelling extreme multivariate events. J R Stat Soc B 53(2):377–392Google Scholar
  7. Davison AC, Smith RL (1990) Models for exceedances over high thresholds (with discussion). J R Stat Soc B 52(3):393–442Google Scholar
  8. de Carvalho M (2016) Statistics of extremes: challenges and opportunities. In: Longin F (ed) Extreme events in finance: a handbook of extreme value theory and its applications. Wiley, HobokenGoogle Scholar
  9. de Carvalho M, Davison AC (2011) Semiparametric estimation for K-sample multivariate extremes. In: Proceedings of 58th International Statistical Institute, pp 2961–2969Google Scholar
  10. de Carvalho M, Davison AC (2014) Spectral density ratio models for multivariate extremes. J Am Stat Assoc 109(506):764–776CrossRefGoogle Scholar
  11. de Carvalho M, Oumow B, Segers J, Warchoł M (2013) A Euclidean likelihood estimator for bivariate tail dependence. Commun Stat Theory Methods 42(7):1176–1192CrossRefGoogle Scholar
  12. de Haan L, Resnick SI (1977) Limit theory for multivariate sample extremes. Zeitsch Wahr Verw Geb 40(4):317–377CrossRefGoogle Scholar
  13. Dunson DB, Pillai N, Park JH (2007) Bayesian density regression. J R Stat Soc B 69(2):163–183CrossRefGoogle Scholar
  14. Eastoe EF, Tawn JA (2009) Modelling non-stationary extremes with application to surface level ozone. J R Stat Soc C 58(1):25–45CrossRefGoogle Scholar
  15. Einmahl J, Segers J (2009) Maximum empirical likelihood estimation of the spectral measure of an extreme-value distribution. Ann Stat 37(5B):2953–2989CrossRefGoogle Scholar
  16. Fernández-Ponce JM, Rodríguez-Griñolo MR (2015) Testing exponentiality against NBUE distributions with an application in environmental extremes. Stoch Environ Res Risk Assess 29(3):679–692CrossRefGoogle Scholar
  17. Ferrez J, Davison AC, Rebetez M (2011) Extreme temperature analysis under forest cover compared to an open field. Agric For Meteorol 151(7):992–1001CrossRefGoogle Scholar
  18. Hainy M, Müller WG, Wagner H (2016) Likelihood-free simulation-based optimal design with an application to spatial extremes. Stoch Environ Res Risk Assess 30(2):481–492. doi: 10.1007/s00477-015-1067-8 CrossRefGoogle Scholar
  19. Hardle W (1990) Applied nonparametric regression. Cambridge University Press, CambridgeCrossRefGoogle Scholar
  20. Huser R, Genton MG (2016) Non-stationary dependence structures for spatial extremes, Journal of Agricultural, Biological, and Environmental Statistics (to appear)Google Scholar
  21. Kiriliouk A, Segers J, Warchoł M (2015) Nonparametric estimation of extremal dependence. In: Dey D, Yan J (eds) Extreme value modelling and risk analysis: methods and applications. Chapman and Hall/CRC, Boca RatonGoogle Scholar
  22. Nadaraya EA (1964) On estimating regression. Theory Probab Appl 9(1):141–142CrossRefGoogle Scholar
  23. Owen A (2001) Empirical Likelihood. Chapman & Hall, Boca RatonCrossRefGoogle Scholar
  24. Pickands J (1981) Multivariate extreme value distributions. In: Proceedings 43rd session International Statistical Institute, pp 859–878Google Scholar
  25. R Core Team (2014) R: a language and environment for statistical computing. R Foundation for Statistical Computing, ViennaGoogle Scholar
  26. Wand MP, Jones MC (1994) Kernel smoothing. Chapman & Hall/CRC, Boca RatonGoogle Scholar
  27. Wang H, Chen Y, Weihong L (2014) Hydrological extreme variability in the headwater of Tarim River: links with atmospheric teleconnection and regional climate. Stoch Environ Res Risk Assess 28(2):443–453CrossRefGoogle Scholar
  28. Watson GS (1964) Smooth regression analysis. Sankhyā 26(4):359–372Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  1. 1.KAUSTThuwalSaudi Arabia
  2. 2.Pontificia Universidad Católica de ChileSantiagoChile

Personalised recommendations