Abstract
There is always a trade off between computational and statistical efficiency. The phenomenal recent advances in computing have shifted the advantage toward Bayesian methods of estimation. We propose an interactive program for analyzing observations above a high threshold. The first phase of the analysis is the “identification” phase. Using parameter estimators which are not too efficient but easy to compute, we perform many iterations to find the empirical optimal combination choice of threshold and choice of monotone increasing function transformation. We review existing methods of estimation. The second phase is the “estimation” phase. We examine the use of Bayes estimators for this phase. We also suggest a method of finding confidence regions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Arnold B. C. and Press S. J., Bayesian analysis of censored or group data from Pareto populations, Bayesian Inference and Decision Techniques: Essays in Honor of Bruno de Finetti. (1986), 157–173.
Beirlant J. and Teugels J. K., The asymptotic behavior of Hill’s estimator, Ther. Prob. Appl. 31, (1986), 463–469.
Castillo E., Extreme Value Theory in Engineering., Academic Press, New York, (1987).
Csörgö S., Deheuvels P. and Mason D., Kernel estimates of the tail index of a distribution, Ann. Statist 13, (1985), 1050–77.
Dargahi-Noubari G. R., On tail estimation, an improved method, Mathematical Geology. 21, (1989), 829–842.
Dargahi-Noubari G. R., On distribution of large incomes, (1993), Submitted.
Davison A. C., Modeling excesses over high thresholds with an application, Statistical extremes and applications (eds.: J. Tiago de Oliveira ), Reidel, Dordrecht, (1984), pp 461–482.
Davison A. C. and Smith R. L., Models for exceedances over high thresholds (with comments), J. Royal Statist Soc. B. 52, (1990), 393–442.
Deheuvels P., Almost sure convergence of the Hill estimator, Math. Proc. Cambridge Phil. Soc. 104, (1988), 371–381.
Dekkers A. L. M. and de Haan L., On the estimation of the extreme value index and large quantile estimation, Ann. Statist. 17, (1989), 1795–1832.
Dekkers A. L. M., Einmahl H. J. and de Haan L., A moment estimator for the index of an extreme value distribution, Ann. Statist 17, (1989), 1833–55.
Galambos J., The asymptotic theory of extreme order statistics. 2ed., Robert E. Krieger Publishing Co., Malabar Fla., (1987).
Grimshaw S. D., A unification of tail estimators, Communications in Statistics. 19, (1990), 4841–57.
Grimshaw S. D., Computing maximum likelihood estimates for the Generalized Pareto distribution, Technometrics. 35, No. 2, (1993), 185–191.
Gumbel E. J., Statistics of Extremes, Columbia Univ. Press, New York, (1958).
Haeusler E. and Teugels J. L., On asymptotic normality of Hill’s estimator for the exponent of regular variation, Ann. Statist 13, (1985), 743–756.
Hartigan J. A., Bayes Theory, Springer Verlag, New York, (1983).
Hill B. M., A simple general approach to inference about the tail of a distribution, Ann. Statist 3, (1975), 1163–1179.
Hosking J. R. M. and Wailis J. R., Parameter and quantile estimation for the generalized Pareto distribution, Technometrics. 29, (1987), 339–349.
Joe H., Estimation of the quantiles of the maximum of N observations, Biornetrika. 71 (1987), 347–354.
Leadbetter M. R., Lindgren G. and Rootzen H., Extremes and related properties of the random sequences and processes, Springer, New York, (1983).
Pickands J. III, Statistical inference using extreme order statistics, Ann. Statist 3, (1975), 119–131.
Pickands J. III, Spline and isotonic estimation of the Pareto function, In: Statistical Extremes and Applications Proceedings of the NATO symposium on extreme values (eds.: J. Tiago de Oliveira ), Reindel Publ. Co., (1984), pp 285–296.
Pickands J. III, The continuous and differentiate domains of attraction of the extreme value distributions, Ann. Probab. Vol. 14, No. 5, (1986), 996–1004.
Ross W. H., A peaks over threshold analysis of extreme wind speeds, Canadian J. Statist 15, (1987), 328–335.
Smith J. A., Estimating the upper tail of flood frequency distributions, Water Resources Research, Amer. Geophysical Research. 23, (1987), 1657–66.
Smith R. L., Maximum likelihood estimation in a class of nonregular cases, Biornetrika 72, (1985), 67–90.
Smith R. L., Estimating tails of probability distributions, Ann. Statist. 15, (1987), 1174–1207.
Smith R. L. and Naylor J. C., A comparison of maximum likelihood and Bayesian estimators for the three parameter Weibull distribution, Appl. Statist. 36, (1987), 359–369.
Smith R. L. and Weissman I., Maximum likelihood estimator of the lower tail of a probability distribution, Journal of the Royal Statistical Society, Ser. B 47, (1985), 285–298.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1994 Kluwer Academic Publishers
About this chapter
Cite this chapter
Pickands, J. (1994). Bayes Quantile Estimation and Threshold Selection for the Generalized Pareto Family. In: Galambos, J., Lechner, J., Simiu, E. (eds) Extreme Value Theory and Applications. Springer, Boston, MA. https://doi.org/10.1007/978-1-4613-3638-9_7
Download citation
DOI: https://doi.org/10.1007/978-1-4613-3638-9_7
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-3640-2
Online ISBN: 978-1-4613-3638-9
eBook Packages: Springer Book Archive