Abstract
Tail data are often modelled by fitting a generalized Pareto distribution (GPD) to the exceedances over high thresholds. In practice, a threshold \(u\) is fixed and a GPD is fitted to the data exceeding \(u\). A difficulty in this approach is the selection of the threshold above which the GPD assumption is appropriate. Moreover the estimates of the parameters of the GPD may depend significantly on the choice of the threshold selected. Sensitivity with respect to the threshold choice is normally studied but typically its effects on the properties of estimators are not accounted for. In this paper, to overcome the difficulties of the fixed-threshold approach, we propose to model extreme and non-extreme data with a distribution composed of a piecewise constant density from a low threshold up to an unknown end point \(alpha\) and a GPD with threshold \(alpha\) for the remaining tail part. Since we estimate the threshold together with the other parameters of the GPD we take naturally into account the threshold uncertainty. We will discuss this model from a Bayesian point of view and the method will be illustrated using simulated data and a real data set.
Similar content being viewed by others
References
Behrens, C.N., Lopes, H.F., Gamerman, D.: Bayesian analysis of extreme events with threshold estimation. Stat. model. 4, 227–244 (2004)
Bermudez, P. de Zea, Amaral Turkman, M.A., Turkman, K.F.: A predictive approach to tail probability estimation. Extremes 4, 295–314 (2002)
Coles, S.G.: An Introduction to Statistical Modelling of Extreme Values. Springer, Berlin Heidelberg New York (2001)
Coles, S.G., Pericchi, L.: Anticipating catastrophes through extreme value modelling. Appl. Stat. 52, 405–416 (2003)
Coles, S.G., Powell, E.A.: Bayesian methods in extreme value modelling: a review and new developments. Int. Statist. Rev. 64, 119–136 (1996)
Coles, S.G., Tawn, J.A.: A Bayesian analysis of extreme rainfall data. Appl. Stat. 45, 463–478 (1996)
Conigliani, C., Tancredi, A.: Semi-parametric modelling for costs of health care technologies. Stat. Med. 24, 3171–3184 (2005)
Davison, A.C., Ramesh, N.I.: Local likelihood smoothing of sample extremes. J. R. Statis. Soc. B 62, 191–208 (2000)
Davison, A.C., Smith, R.L.: Models for exceedances over high thresholds (with discussion). J. R. Statis. Soc. B 52, 393–442 (1990)
Draper, D.: Assessment and propagation of model uncertainty (with discussion). J. R. Statis. Soc. B 57, 45–97 (1995)
Dupius, D.J.: Exceedances over high thresholds: a guide to threshold selection. Extremes 1, 251–261 (1998)
Embrechts, P., Kluppelberg, C., Mikosh T.: Modelling Extremal Events. Springer, Berlin Heidelberg New York (1997)
Frigessi, A., Haug, O., Rue, H.: A dynamic mixture model for unsupervised tail estimation without threshold selection. Extremes 5, 219–235 (2002)
Green, P.J.: Reversible jump Markov chain Monte Carlo computation and Bayesian model determination. Biometrika 82, 711–732 (1995)
Guillou, A., Hall, P.: A diagnostic for selecting the threshold in extreme value theory. J. R. Statis. Soc. B 63, 293–305 (2001)
Heffernan, J.E., Tawn, J.A.: A conditional approach for multivariate extreme values. J. R. Statis. Soc. B 66, 1–34 (2004)
Hjort, N.L., Claeskens, G.: Frequentist model average estimators. J. Am. Stat. Assoc. 98, 879–899 (2003)
Hosking, J., Wallis, J.R.: Parameter and quantile estimation for the generalized Pareto distribution. Technometrics 29, 339–349 (1987)
Natural Environment Research Council: Flood Studies Report. NERC, London (1975)
Pauli, F., Coles, S.G.: Penalized likelihood inference in extreme value theory. J. Appl. Stat. 28, 547–560 (2001)
Pickands, J.: Statistical inference using extreme order statistics. Ann. Statist. 3, 119–131 (1975)
Robert, C.P.: Discretization and MCMC Convergence Assessment. Lecture Notes in Statistics 135. Springer, Berlin Heidelberg New York (1998)
Robert, C.P., Casella, G.: Monte Carlo Statistical Methods. Springer, Berlin Heidelberg New York (1999)
Smith, R.L.: Extreme value analysis of environmental time series: an application to trend detection in ground-level ozone. Stat. Sci. 4, 367–393 (1989)
Tanner, M.A.: Tools For Statistical Inference, 2nd edn. Springer, Berlin Heidelberg New York (1993)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Tancredi, A., Anderson, C. & O’Hagan, A. Accounting for threshold uncertainty in extreme value estimation. Extremes 9, 87–106 (2006). https://doi.org/10.1007/s10687-006-0009-8
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10687-006-0009-8
Keywords
- Extreme value theory
- Generalized Pareto distribution
- Reversible jump algorithm
- Threshold estimation
- Uniform mixtures