Threshold selection for regional peaks-over-threshold data. (English) Zbl 1514.62830
Summary: A hurdle in the peaks-over-threshold approach for analyzing extreme values is the selection of the threshold. A method is developed to reduce this obstacle in the presence of multiple, similar data samples. This is for instance the case in many environmental applications. The idea is to combine threshold selection methods into a regional method. Regionalized versions of the threshold stability and the mean excess plot are presented as graphical tools for threshold selection. Moreover, quantitative approaches based on the bootstrap distribution of the spatially averaged Kolmogorov-Smirnov and Anderson-Darling test statistics are introduced. It is demonstrated that the proposed regional method leads to an increased sensitivity for too low thresholds, compared to methods that do not take into account the regional information. The approach can be used for a wide range of univariate threshold selection methods. We test the methods using simulated data and present an application to rainfall data from the Dutch water board Vallei en Veluwe.
MSC:
| 62-XX | Statistics |
Software:
ismevReferences:
| [1] | M.A. Ancona-Navarrete and J.A. Tawn, Diagnostics for pairwise extremal dependence in spatial processes, Extremes 5 (2002), pp. 271-285. doi: 10.1023/A:1024029128431 · Zbl 1036.62094 · doi:10.1023/A:1024029128431 |
| [2] | S. Beguería, M. Angulo-Martínez, S.M. Vicente-Serrano, J.I. López-Moreno, and A. El-Kenawy, Assessing trends in extreme precipitation events intensity and magnitude using non-stationary peaks-over-threshold analysis: A case study in northeast Spain from 1930 to 2006, Int. J. Climatol. 31 (2010), pp. 2102-2114. doi: 10.1002/joc.2218 · doi:10.1002/joc.2218 |
| [3] | T.A. Buishand, Bivariate extreme-value data and the station-year method, J. Hydrol. 69 (1984), pp. 77-95. doi: 10.1016/0022-1694(84)90157-4 · doi:10.1016/0022-1694(84)90157-4 |
| [4] | T.A. Buishand, G. De Martino, J.N. Spreeuw, and T. Brandsma, Homogeneity of precipitation series in the Netherlands and their trends in the past century, Int. J. Climatol. 33 (2013), pp. 815-833. doi: 10.1002/joc.3471 · doi:10.1002/joc.3471 |
| [5] | V. Choulakian and M.A. Stephens, Goodness-of-fit tests for the generalized Pareto distribution, Technometrics 43 (2001), pp. 478-484. doi: 10.1198/00401700152672573 |
| [6] | S. Coles, An Introduction to Statistical Modeling of Extreme Values, Springer, London, 2001. · Zbl 0980.62043 · doi:10.1007/978-1-4471-3675-0 |
| [7] | S. Coles, J. Heffernan, and J.A. Tawn, Dependence measures for extreme value analyses, Extremes 2 (1999), pp. 339-365. doi: 10.1023/A:1009963131610 · Zbl 0972.62030 · doi:10.1023/A:1009963131610 |
| [8] | A.C. Davison, S.A. Padoan, and M. Ribatet, Statistical modeling of spatial extremes, Statist. Sci. 27 (2012), pp. 161-186. doi: 10.1214/11-STS376 · Zbl 1330.86021 · doi:10.1214/11-STS376 |
| [9] | A.C. Davison and R.L. Smith, Models for exceedances over high thresholds, J. R. Stat. Soc. B 52 (1990), pp. 393-442. · Zbl 0706.62039 |
| [10] | E.M. Douglas, R.M. Vogel, and C.N. Kroll, Trends in floods and low flows in the United States: Impact of spatial correlation, J. Hydrol. 240 (2000), pp. 90-105. doi: 10.1016/S0022-1694(00)00336-X · doi:10.1016/S0022-1694(00)00336-X |
| [11] | M.-A. El-Aroui and J. Diebolt, On the use of the peaks over thresholds method for estimating out-of-sample quantiles, Comput. Statist. Data Anal. 39 (2002), pp. 453-475. doi: 10.1016/S0167-9473(01)00087-1 · Zbl 1101.62337 · doi:10.1016/S0167-9473(01)00087-1 |
| [12] | P. Embrechts, C. Klüppelberg, and T. Mikosch, Modelling Extremal Events, Springer, Berlin, 1997. · Zbl 0873.62116 · doi:10.1007/978-3-642-33483-2 |
| [13] | H.J. Fowler, M. Ekström, C.G. Kilsby, and P.D. Jones, New estimates of future changes in extreme rainfall across the UK using regional climate model integrations. 1. Assessment of control climate, J. Hydrol. 300 (2005), pp. 212-233. doi: 10.1016/j.jhydrol.2004.06.017 · doi:10.1016/j.jhydrol.2004.06.017 |
| [14] | S. Ghosh and S. Resnick, A discussion on mean excess plots, Stochastic Process. Appl. 120 (2010), pp. 1492-1517. doi: 10.1016/j.spa.2010.04.002 · Zbl 1195.62068 · doi:10.1016/j.spa.2010.04.002 |
| [15] | P. Hall and A.H. Welsh, Adaptive estimates of parameters of regular variation, Ann. Statist. 13 (1985), pp. 331-341. doi: 10.1214/aos/1176346596 · Zbl 0605.62033 · doi:10.1214/aos/1176346596 |
| [16] | M. Hanel, T.A. Buishand, and C.A.T. Ferro, A nonstationary index flood model for precipitation extremes in transient regional climate model simulations, J. Geophys. Res. 114 (2009), p. D15107. doi:10.1029/2009JD011712. · doi:10.1029/2009JD011712 |
| [17] | J.L. Hintze and R.D. Nelson, Violin plots: A box plot-density trace synergism, Amer. Statist. 52 (1998), pp. 181-184. |
| [18] | L. Holden and O. Haug, A Multidimensial Mixture Model for Unsupervised Tail Estimation, Samba/09/09, Norwegian Computer Center, 2009. |
| [19] | J.R.M. Hosking and J.R. Wallis, Regional Frequency Analysis: An Approach Based on L-Moments, Cambridge University Press, Cambridge, 1997. · doi:10.1017/CBO9780511529443 |
| [20] | D. Koutsoyiannis, Statistics of extremes and estimation of extreme rainfall: II. Empirical investigation of long rainfall records, Hydrolog. Sci. J. 49 (2004), pp. 591-610. |
| [21] | J. Kyselý and R. Beranová, Climate-change effects on extreme precipitation in central Europe: Uncertainties of scenarios based on regional climate models, Theory Appl. Climatol. 95 (2009), pp. 361-374. doi: 10.1007/s00704-008-0014-8 · doi:10.1007/s00704-008-0014-8 |
| [22] | J. Kyselý, J. Picek, and R. Beranová, Estimating extremes in climate change simulations using the peaks-over-threshold method with a non-stationary threshold, Global Planet. Change 72 (2010), pp. 55-68. doi: 10.1016/j.gloplacha.2010.03.006 · doi:10.1016/j.gloplacha.2010.03.006 |
| [23] | H. Madsen and D. Rosbjerg, The partial duration series method in regional index-flood modeling, Water Resour. Res. 33 (1997), pp. 737-746. doi: 10.1029/96WR03847 · doi:10.1029/96WR03847 |
| [24] | R.B. Nelsen, An Introduction to Copulas, Springer, New York, 2006. · Zbl 1152.62030 |
| [25] | S.M. Papalexiou and D. Koutsoyiannis, Battle of extreme value distributions: A global survey on extreme daily rainfall, Water Resour. Res. 49 (2013), pp. 187-201. doi: 10.1029/2012WR012557 · doi:10.1029/2012WR012557 |
| [26] | J.I. Pickands, Statistical inference using extreme order statistics, Ann. Statist. 3 (1975), pp. 119-131. doi: 10.1214/aos/1176343003 · Zbl 0312.62038 · doi:10.1214/aos/1176343003 |
| [27] | R.D. Reiss and M. Thomas, Statistical Analysis of Extreme Values: With Applications to Insurance, Finance, Hydrology and Other Fields, 3rd ed., Birkhäuser, Basel, 2007. · Zbl 1122.62036 |
| [28] | M. Ribatet, E. Sauquet, J.-M . Grésillon, and T.B.M.J. Ouarda, A regional Bayesian POT model for flood frequency analysis, Stoch. Env. Res. Risk A. 21 (2007), pp. 327-339. doi: 10.1007/s00477-006-0068-z · Zbl 1405.86026 · doi:10.1007/s00477-006-0068-z |
| [29] | M. Roth, T.A. Buishand, G. Jongbloed, A.M.G. Klein Tank, and J.H. van Zanten, A regional peaks-over-threshold model in a nonstationary climate, Water Resour. Res. 48 (2012), p. W11533. doi:10.1029/2012WR012214. · doi:10.1029/2012WR012214 |
| [30] | M. Roth, T.A. Buishand, G. Jongbloed, A.M.G. Klein Tank, and J.H. van Zanten, Projections of precipitation extremes based on a regional, non-stationary peaks-over-threshold approach: A case study for the Netherlands and north-western Germany, Weather Climate Extremes 4 (2014), pp. 1-10. doi: 10.1016/j.wace.2014.01.001 · doi:10.1016/j.wace.2014.01.001 |
| [31] | C. Scarrott and A. MacDonald, A review of extreme value threshold estimation and uncertainty quantification, REVSTAT 10 (2012), pp. 33-60. · Zbl 1297.62120 |
| [32] | J. Segers, Max-stable models for multivariate extremes, REVSTAT 10 (2012), pp. 61-82. · Zbl 1297.62121 |
| [33] | F. Serinaldi and C.G. Kilsby, Rainfall extremes: toward reconciliation after the battle of distributions, Water Resour. Res. 50 (2014), pp. 336-352. doi: 10.1002/2013WR014211 · doi:10.1002/2013WR014211 |
| [34] | R.L. Smith, Extreme value theory, in Handbook of Applicable Mathematics Supplement, W. Ledermann, E. Lloyd, S. Vajda, and C. Alexander, eds., Chapter 14, Wiley, Chichester, 1990, pp. 437-472. |
| [35] | C. Svensson and D.A. Jones, Review of rainfall frequency estimation methods, J. Flood Risk Manage. 3 (2010), pp. 296-313. doi: 10.1111/j.1753-318X.2010.01079.x · doi:10.1111/j.1753-318X.2010.01079.x |
| [36] | E. Thibaud, R. Mutzner, and A.C. Davison, Threshold modeling of extreme spatial rainfall, Water Resour. Res. 49 (2013), pp. 4633-4644. doi: 10.1002/wrcr.20329 · doi:10.1002/wrcr.20329 |
| [37] | P. Thompson, Y. Cai, D. Reeve, and J. Stander, Automated threshold selection methods for extreme wave analysis, Coast. Eng. 56 (2009), pp. 1013-1021. doi: 10.1016/j.coastaleng.2009.06.003 · doi:10.1016/j.coastaleng.2009.06.003 |
| [38] | J.L. Wadsworth and J.A. Tawn, Likelihood-based procedures for threshold diagnostics and uncertainty in extreme value modelling, J. R. Stat. Soc. B 74 (2012), pp. 543-567. doi: 10.1111/j.1467-9868.2011.01017.x · Zbl 1411.62127 · doi:10.1111/j.1467-9868.2011.01017.x |
| [39] | Y. Wang, Jump and sharp cusp detection by wavelets, Biometrika 82 (1995), pp. 385-397. doi: 10.1093/biomet/82.2.385 · Zbl 0824.62031 · doi:10.1093/biomet/82.2.385 |
| [40] | J. Weiss and P. Bernardara, Comparison of local indices for regional frequency analysis with an application to extreme skew surges, Water Resour. Res. 49 (2013), pp. 2940-2951. doi: 10.1002/wrcr.20225 · doi:10.1002/wrcr.20225 |
| [41] | J. Zhang and M.A. Stephens, A new and efficient estimation method for the generalized Pareto distribution, Technometrics 51 (2009), pp. 316-325. doi: 10.1198/tech.2009.08017 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
