Extreme value theory based on the r largest annual events

doi:10.1016/0022-1694(86)90004-1

Journal of Hydrology

Volume 86, Issues 1–2, September 1986, Pages 27-43

https://doi.org/10.1016/0022-1694(86)90004-1 Get rights and content

Abstract

We present a family of statistical distributions and estimators for extreme values based on a fixed number r ⩾ 1 of the largest annual events. The distributions are based on the asymptotic joint distribution of the r largest values in a single sample, and the method of estimation is numerical maximum likelihood. The method is illustrated by an application to the sea levels in Venice, with particular attention to questions concerning trend and periodicity. Theoretical calculations are given for the asymptotic efficiency of the method.

References (8)

E.J. Gumbel
Statistics of Extremes
(1958)
J.R.M. Hosking
Testing whether the shape parameter is zero in the generalized extreme-value distribution
Biometrika
(1984)
M.R. Leadbetter et al.
Extremes and Related Properties of Random Sequences and Series
(1983)
P. Pirazzoli
Maree estreme a Venezia (periodo 1872–1981)
Acqua Aria
(1982)

There are more references available in the full text version of this article.

Cited by (151)

Modeling climate extremes using the four-parameter kappa distribution for r-largest order statistics
2023, Weather and Climate Extremes
Accurate estimation of the T-year return levels of climate extremes using statistical distribution is a critical step in the projection of future climate and in engineering design for disaster response. We show how the estimation of such quantities can be improved by fitting the four-parameter kappa distribution for $r$ -largest order statistics (rK4D), which was developed in this study. The rK4D is an extension of the generalized extreme value distribution for $r$ -largest order statistics (rGEVD), similar to the four-parameter kappa distribution (K4D), which is an extension of the generalized extreme value distribution (GEVD). This new distribution (rK4D) can be useful not only for fitting data when three parameters in the GEVD are not sufficient to capture the variability of the extreme observations, but also in reducing the estimation uncertainty by making use of the r-largest extreme observations instead of only the block maxima. We derive a joint probability density function (PDF) of rK4D and the marginal and conditional cumulative distribution functions and PDFs. To estimate the parameters, the maximum likelihood estimation and the maximum penalized likelihood estimation methods were considered. The usefulness and practical effectiveness of the rK4D are illustrated by the Monte Carlo simulation and by an application to the Bangkok extreme rainfall data. A few new distributions for $r$ -largest order statistics are also derived as special cases of the rK4D, such as the $r$ -largest logistic, the $r$ -largest generalized logistic, and the $r$ -largest generalized Gumbel distributions. These distributions for $r$ -largest order statistics would be useful in modeling extreme values for many research areas, including hydrology and climatology.
New Zealand design wind speeds, directional and lee-zone multipliers proposed for AS/NZS 1170.2:2021
2021, Journal of Wind Engineering and Industrial Aerodynamics
The study aims to estimate design wind speeds and associated directional multipliers, also lee-zone multipliers for New Zealand through the analysis of historical wind data recorded at meteorological stations and also utilising a high-resolution convection-resolving numerical weather prediction model (New Zealand Convective-Scale Model (NZCSM)) analyses. New Zealand’s historical wind data have not been analysed in the past two decades for design wind-load purposes. In addition, no attempt has been made to thoroughly homogenise the mean and gust wind speed data recorded prior to the 1990s and to convert them to equivalent Automatic Weather Stations (AWS) records. Furthermore, lee zones, areas affected by the wind speed-up due to the presence of mountains, can significantly influence the design wind loads, thus, it is crucial to estimate the spatial extent and magnitude of the lee multiplier accurately. In this study, the wind data were initially subjected to a robust homogenisation algorithm and then, they were separated into synoptic and non-synoptic events to gain a better understanding of New Zealand’s gust climatology and sources of extreme events. It was demonstrated that synoptic events dominate the design wind speeds at most locations in New Zealand. For extreme value analysis, three different extreme value distributions were used, namely Type I (using Gumbel, Gringorten and BLUE fitting methods), Type III (using maximum likelihood and probability weighted moments methods), and Peaks-Over-Threshold (POT) approach. In addition, the predictions of NZCSM along with historical wind speeds were used to identify the lee zones, which confirms existing zones and provides evidence to support introducing new zones, and obtain estimates of the lee-multipliers. Substantial changes have been proposed for the next version of the Australian/New Zealand wind-loading standard (AS/NZS 1170.2) based on the results of this study. The changes include adding a new wind region to New Zealand, refinements of wind zone boundaries, revising all regional wind speeds and directional multipliers, and modifying the lee-zone regions and multipliers.
Wave modeling of a reef-sheltered coastal zone in the Red Sea
2020, Ocean Engineering
Citation Excerpt :
GEV estimates the wave height with certain return periods based on block maxima, which are typically the annual maxima (Leadbetter et al., 1983), and GPD follows a peak over threshold (POT) approach in which it includes all the local maxima or storm peaks above a certain threshold. As the annual maxima do not provide a suitable sample for estimating the extremes, we adopted the r-largest method (Smith, 1986) for our GEV analysis, which considers a number of the largest observations from a block period. Block period refers to dividing the total length of data into non-overlapping periods of equal size and then focusing on the maximum value within each period.
The coastal areas of the Red Sea are characterized by shallow banks of fringing and barrier reefs that provide protection against coastal hazards and erosion by dissipating wave energy. This study investigates the wave climate and extremes of a reef-protected coastal zone in the Red Sea using a high-resolution coupled wave and circulation model, ADCIRC + SWAN, configured on an unstructured grid forced with the meteorological fields from high-resolution regional atmospheric model. Our simulations suggest that the relatively narrow offshore reefs with steep fore-reef slopes dissipate 40–50% of the wave energy propagating towards the shoreline, and this is more pronounced during extremes. The impact of the coupling on determining the wave climate is negligible, but is significant for storms with ~10 cm higher significant wave height (Hs) during the observed period. The back-reef wave climatology computed from 30-year model simulations shows that the mean Hs distribution is uniform throughout the year, and extremes occur more often from February to May. Different return levels of Hs in the sheltered areas are estimated using extreme value analysis. Our results emphasize that preserving the complex offshore reefs is crucial for mitigating the coastal hazards of high-energy waves which are projected to increase with climate change.
A change-point model for the r-largest order statistics with applications to environmental and financial data
2020, Applied Mathematical Modelling
Citation Excerpt :
In addition, the approximation of the GEVr distribution becomes weak because of a decreased convergence rate. If the choice of r is small, the variance of the estimator may increase [9]. Thus, an optimal r is needed to ensure efficient estimators for the parameters of the GEVr distribution and to improve the characterization of the data.
This study makes a new contribution to extreme value theory by proposing a change-point model of the distribution of the r-larger order statistics. In some situations, using only the maxima of grouped data results in a small sample size that may require a larger dataset. In this sense, using the joint distribution of the r-largest order statistics provides more information and, consequently, better estimators. We perform a comprehensive simulation to show the advantage of this method over other competitive models that approach the change-point model in extremes. Finally, the proposed model is fitted to river quota data (environmental data) and NASDAQ daily returns data (financial data) to demonstrate its potential for practical application.
Generalized logistic model for r largest order statistics, with hydrological application
2024, Stochastic Environmental Research and Risk Assessment
Load Spectra Extrapolation by Bandwidth-Optimized Kernel Density Estimation Based on DBSCAN Algorithm
2024, Journal of Vibration Engineering and Technologies

View all citing articles on Scopus

^∗: Present address: Department of Mathematics, University of Surrey, Guildford, GU2 5XH, U.K.

View full text

Extreme value theory based on the r largest annual events

Abstract

Statistics of Extremes

Testing whether the shape parameter is zero in the generalized extreme-value distribution

Biometrika

Extremes and Related Properties of Random Sequences and Series

Maree estreme a Venezia (periodo 1872–1981)

Acqua Aria