Environmental and Ecological Statistics

, Volume 14, Issue 3, pp 285–299 | Cite as

Time-varying models for extreme values

  • Gabriel Huerta
  • Bruno Sansó


We propose a new approach for modeling extreme values that are measured in time and space. First we assume that the observations follow a Generalized Extreme Value (GEV) distribution for which the location, scale or shape parameters define the space–time structure. The temporal component is defined through a Dynamic Linear Model (DLM) or state space representation that allows to estimate the trend or seasonality of the data in time. The spatial element is imposed through the evolution matrix of the DLM where we adopt a process convolution form. We show how to produce temporal and spatial estimates of our model via customized Markov Chain Monte Carlo (MCMC) simulation. We illustrate our methodology with extreme values of ozone levels produced daily in the metropolitan area of Mexico City and with rainfall extremes measured at the Caribbean coast of Venezuela.


Spatio-temporal process Extreme values GEV distribution Process convolutions MCMC Ozone levels 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Assunção CBN, Gamerman D and Lopes HF (2004). Bayesian analysis of extreme events with threshold estimation. Stat Model, 4: 227–244 CrossRefGoogle Scholar
  2. 2.
    Carter CK and Kohn R (1994). On Gibbs sampling for state space models. Biometrika 81: 541–553 CrossRefGoogle Scholar
  3. 3.
    Casson E and Coles S (1999). Spatial regression models for extremes. Extremes 1: 449–468 CrossRefGoogle Scholar
  4. 4.
    Coles S (2001). An introduction to statistical modeling of extreme values. Springer-Verlag, New York USA Google Scholar
  5. 5.
    Coles S, Heffernan JE and Tawn JA (1999). Dependence measures for extreme value analyses. Extremes 2(4): 339–365 CrossRefGoogle Scholar
  6. 6.
    Coles S and Tawn JE (1996). A Bayesian analysis of extreme rainfall data. Appl Stat 45: 463–478 CrossRefGoogle Scholar
  7. 7.
    Coles SG, Pericchi LR and Sisson SA (2003). A fully probabilistic approach to extreme value modelling. J Hydrol 273: 45–50 CrossRefGoogle Scholar
  8. 8.
    Davison AC and Smith RL (1990). Models for exceedances over high thresholds (with comments). J Roy Stat Soc Ser B Methodol 52: 393–442 Google Scholar
  9. 9.
    Dupuis D (2005) Ozone concentrations: a robust analysis of multivariate extremes. Technometrics (To appear)Google Scholar
  10. 10.
    Frühwirth-Schnatter S (1994). Data augmentation and dynamic linear models. J Time Ser Anal 15: 183–202 Google Scholar
  11. 11.
    Gaetan C and Grigoletto M (2004). Smoothing sample extremes with dynamic models. Extremes 7: 221–236 CrossRefGoogle Scholar
  12. 12.
    Gamerman D (1997). Markov Chain Monte Carlo. Chapman and Hall, London UK Google Scholar
  13. 13.
    Gilleland E, Nychka D, Schneider U (2004) Spatial models for the distribution of extremes. Tech. rep., Geophysical Statistics Project, NCAR. Summer Institute at the Center on Global Change, Duke University.Google Scholar
  14. 14.
    Heffernan JE and Tawn JA (2004). A conditional approach for multivariate extreme values (with discussion). J R Stat Soc B 66: 497–546 CrossRefGoogle Scholar
  15. 15.
    Higdon D (2002). Space and space-time modeling using process convolutions. In: Anderson, C, Barnett, V, Chatwin, PC and El-Shaarawi, AH (eds) Quantitative methods for current environmental issues, pp 37–56. Springer Verlag, London Google Scholar
  16. 16.
    Huerta G, Sansó B and Stroud JR (2004). A spatio-temporal model for Mexico city ozone levels. Appl Stati 53: 231–248 Google Scholar
  17. 17.
    Kern J (2000) Bayesian process-convolution approaches to specifying spatial dependence structure. Ph.D. thesis, Institute of Statistics and Decision Sciences, Duke University, Durham, North Carolina, USAGoogle Scholar
  18. 18.
    Kim S, Shephard N and Chib S (1998). Stochastic volatility: likelihood inference and comparison with arch models. Rev Fin Stud 65: 361–393 Google Scholar
  19. 19.
    Ledford AW and Tawn JA (1996). Statistics for near independence in multivariate extreme values. Biometrika 83: 169–187 CrossRefGoogle Scholar
  20. 20.
    Ledford AW and Tawn JA (1997). Modeling dependence within joint tail regions. J R Stat Soc B 59: 475–499 CrossRefGoogle Scholar
  21. 21.
    Pickands J (1971). The two-dimensional Poisson process and extremal processes. J Appl Probability 8: 745–756 CrossRefGoogle Scholar
  22. 22.
    Pickands J (1975). Statistical inference using extreme order statistics. Ann Stat 3: 119–131 Google Scholar
  23. 23.
    Rosenblatt M (1952). Remarks on a multivariate transformation. Ann Math Stat 23: 470–472 Google Scholar
  24. 24.
    Smith RL (1989). Extreme value analysis of environmental time series: An application to trend detection in ground-level ozone (C/R: P378-393). Stat Sci 4: 367–377 Google Scholar
  25. 25.
    Smith RL, Tawn JA and Coles SG (1997). Markov chain models for threshold exceedances. Biometrika 84: 249–268 CrossRefGoogle Scholar
  26. 26.
    West M and Harrison J (1997). Bayesian forecasting and dynamic models. Springer Verlag, New York Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  1. 1.Department of Mathematics and StatisticsUniversity of New MexicoAlbuquerqueUSA
  2. 2.Department of Applied Mathematics and StatisticsUniversity of CaliforniaSanta CruzUSA

Personalised recommendations