An Improved Peaks-Over-Threshold Method and its Application in the Time-Varying Design Flood

2021 ◽  
Vol 35 (3) ◽  
pp. 933-948
Author(s):  
Jiqing Li ◽  
Jing Huang ◽  
Xuefeng Chu ◽  
Jay R. Lund
Keyword(s):  
Time Varying ◽  
Peaks Over Threshold ◽  
Design Flood ◽  
Threshold Method

scholarly journals Study on reservoir time-varying design flood of inflow based on Poisson process with time-dependent parameters

2018 ◽  
Vol 379 ◽  
pp. 119-123
Author(s):  
Jiqing Li ◽  
Jing Huang ◽  
Jianchang Li
Keyword(s):  
Poisson Process ◽  
Flood Control ◽  
Time Dependent ◽  
Model Parameters ◽  
Time Varying ◽  
Design Flood ◽  
Threshold Method ◽  
Peak Over Threshold ◽  
Peak Over Threshold Method ◽  
The Relationship

Abstract. The time-varying design flood can make full use of the measured data, which can provide the reservoir with the basis of both flood control and operation scheduling. This paper adopts peak over threshold method for flood sampling in unit periods and Poisson process with time-dependent parameters model for simulation of reservoirs time-varying design flood. Considering the relationship between the model parameters and hypothesis, this paper presents the over-threshold intensity, the fitting degree of Poisson distribution and the design flood parameters are the time-varying design flood unit period and threshold discriminant basis, deduced Longyangxia reservoir time-varying design flood process at 9 kinds of design frequencies. The time-varying design flood of inflow is closer to the reservoir actual inflow conditions, which can be used to adjust the operating water level in flood season and make plans for resource utilization of flood in the basin.

Comparison of Annual Maximum and Peaks Over Threshold Methods with Automated Threshold Selection in Flood Frequency Analysis: A Case Study for Australia

2021 ◽  
Author(s):  
Xiao Pan ◽  
Ataur Rahman
Keyword(s):  
Frequency Analysis ◽  
Flood Frequency ◽  
Distribution Functions ◽  
Flood Frequency Analysis ◽  
Annual Maximum ◽  
Threshold Selection ◽  
Peaks Over Threshold ◽  
Design Flood ◽  
Threshold Detection ◽  
Using Data

Abstract Flood frequency analysis (FFA) enables fitting of distribution functions to observed flow data for estimation of flood quantiles. Two main approaches, Annual Maximum (AM) and peaks-over-threshold (POT) are adopted for FFA. POT approach is under-employed due to its complexity and uncertainty associated with the threshold selection and independence criteria for selecting peak flows. This study evaluates the POT and AM approaches using data from 188 gauged stations in south-east Australia. POT approach adopted in this study applies a different average numbers of events per year fitted with Generalised Pareto (GP) distribution with an automated threshold detection method. The POT model extends its parametric approach to Maximum Likelihood Estimator (MLE) and Point Moment Weighted Unbiased (PMWU) method. Generalised Extreme Value (GEV) distribution using L-moment estimator is used for AM approach. It has been found that there is a large difference in design flood estimates between the AM and POT approaches for smaller average recurrence intervals (ARI), with a median difference of 25% for 1.01 year ARI and 5% for 50 and 100 years ARIs.

The Development of Estimators for the Peaks-Over-Threshold Method

2002 ◽  
Author(s):  
A. Naess ◽  
P. H. Clausen
Keyword(s):  
Wind Speed ◽  
Synthetic Data ◽  
Distribution Functions ◽  
Statistical Distribution ◽  
Peaks Over Threshold ◽  
Threshold Method

The paper discusses the accuracy and efficiency of some of the standard estimators used in conjunction with the Peaks-Over-Threshold (POT) method. A comparison is made between some commonly adopted estimators and two types of estimators proposed by the authors. The comparison is based on an extensive set of synthetic data simulated from a range of different statistical distribution functions that have been assumed to describe wind speed processes.

scholarly journals Extreme value theory in emerging markets: Evidence from the Montenegrin stock exchange

2015 ◽  
Vol 60 (206) ◽  
pp. 87-116 ◽  
Author(s):  
Julija Cerovic ◽  
Vesna Karadzic
Keyword(s):  
At Risk ◽  
Stock Market ◽  
Extreme Value Theory ◽  
Value At Risk ◽  
Emerging Market ◽  
Value Theory ◽  
Extreme Value ◽  
Peaks Over Threshold ◽  
Threshold Method ◽  
Block Maxima

The concept of Value at Risk(VaR) estimates the maximum loss of a financial position at a given time for a given probability. This paper considers the adequacy of the methods that are the basis of extreme value theory in the Montenegrin emerging market before and during the global financial crisis. In particular, the purpose of the paper is to investigate whether the peaks-over-threshold method outperforms the block maxima method in evaluation of Value at Risk in emerging stock markets such as the Montenegrin market. The daily return of the Montenegrin stock market index MONEX20 is analyzed for the period January 2004 - February 2014. Results of the Kupiec test show that the peaks-over-threshold method is significantly better than the block maxima method, but both methods fail to pass the Christoffersen independence test and joint test due to the lack of accuracy in exception clustering when measuring Value at Risk. Although better, the peaks-over-threshold method still cannot be treated as an accurate VaR model for the Montenegrin frontier stock market.

A COMPARISON OF SOME UNIVARIATE MODELS FOR VALUE-AT-RISK AND EXPECTED SHORTFALL

2007 ◽  
Vol 10 (06) ◽  
pp. 1043-1075 ◽  
Author(s):  
CARLO MARINELLI ◽  
STEFANO D'ADDONA ◽  
SVETLOZAR T. RACHEV
Keyword(s):  
At Risk ◽  
Extreme Value Theory ◽  
Value At Risk ◽  
Value Theory ◽  
Extreme Value ◽  
Expected Shortfall ◽  
Stable Laws ◽  
Peaks Over Threshold ◽  
Threshold Method ◽  
Block Maxima

We compare in a backtesting study the performance of univariate models for Value-at-Risk (VaR) and expected shortfall based on stable laws and on extreme value theory (EVT). Analyzing these different approaches, we test whether the sum–stability assumption or the max–stability assumption, that respectively imply α–stable laws and Generalized Extreme Value (GEV) distributions, is more suitable for risk management based on VaR and expected shortfall. Our numerical results indicate that α–stable models tend to outperform pure EVT-based methods (especially those obtained by the so-called block maxima method) in the estimation of Value-at-Risk, while a peaks-over-threshold method turns out to be preferable for the estimation of expected shortfall. We also find empirical evidence that some simple semiparametric EVT-based methods perform well in the estimation of VaR.

scholarly journals Peaks Over Threshold–based detector design for structural health monitoring: Application to aerospace structures

2017 ◽  
Vol 17 (1) ◽  
pp. 91-107 ◽  
Author(s):  
Marc Rébillat ◽  
Ouadie Hmad ◽  
Farid Kadri ◽  
Nazih Mechbal
Keyword(s):  
Structural Health Monitoring ◽  
False Alarm ◽  
Damage Detection ◽  
Health Monitoring ◽  
Value Theory ◽  
Decision Threshold ◽  
Peaks Over Threshold ◽  
Threshold Method ◽  
Structural Health ◽  
Probability Of False Alarm

Structural health monitoring offers new approaches to interrogate the integrity of complex structures. The structural health monitoring process classically relies on four sequential steps: damage detection, localization, classification, and quantification. The most critical step of such process is the damage detection step since it is the first one and because performances of the following steps depend on it. A common method to design such a detector consists of relying on a statistical characterization of the damage indexes available in the healthy behavior of the structure. On the basis of this information, a decision threshold can then be computed in order to achieve a desired probability of false alarm. To determine the decision threshold corresponding to such desired probability of false alarm, the approach considered here is based on a model of the tail of the damage indexes distribution built using the Peaks Over Threshold method extracted from the extreme value theory. This approach of tail distribution estimation is interesting since it is not necessary to know the whole distribution of the damage indexes to develop a detector, but only its tail. This methodology is applied here in the context of a composite aircraft nacelle (where desired probability of false alarm is typically between 10−4 and 10−9) for different configurations of learning sample size and probability of false alarm and is compared to a more classical one which consists of modeling the entire damage indexes distribution by means of Parzen windows. Results show that given a set of data in the healthy state, the effective probability of false alarm obtained using the Peaks Over Threshold method is closer to the desired probability of false alarm than the one obtained using the Parzen-window method, which appears to be more conservative.

Sign in / Sign up

Export Citation Format

Share Document