Comparison of different estimation methods for extreme value distribution

Yılmaz, Asuman; Kara, Mahmut; Özdemir, Onur

doi:10.1080/02664763.2021.1940109

Cited by 4 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this example, the final choice of the Bayesian approach to estimate the GPD model parameters is confirmed in the bottom right panel of Figure 9 which highlights both the best model fit to the top 10 extreme values recorded and satisfactory error estimates. The improved result using the Bayesian estimation method accords with the findings of Yilmaz et al ( 2021) [46].…”

Section: Sensitivity Analysis Testing For Evasupporting

confidence: 88%

“…All the aforementioned factors are most likely to increase in intensity with climate change [46]. Although this study finds no statistical evidence (yet) of an increase in extreme water levels over time (refer to Section 4.1), it is likely that a small positive trend will emerge should the prevalence of extreme events measured over the past two decades continue over the forthcoming decade.…”

Section: The Shape Of the Eva Return Level Plotmentioning

confidence: 60%

“…There are a wide variety of selection techniques which occupy the literature for this type of application. Yilmaz et al (2021) [46] provided a detailed and wide-ranging testing regime of estimation methods for extreme value distributions encompassing classical techniques and Bayesian estimators applied to real-world data. Simulation results show that Bayes methods demonstrate better performance than the classical methods for estimating the unknown parameters.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Extreme Value Analysis of Ocean Still Water Levels along the USA East Coast—Case Study (Key West, Florida)

Watson

2023

Coasts

View full text Add to dashboard Cite

This paper provides an Extreme Value Analysis (EVA) of the hourly still water level (SWL) record at Key West, Florida dating back to 1913 to understand the statistical likelihood of the combination of high predicted tides and the more dynamic influences (predominantly hurricane induced storm surges) that can drive ocean water levels higher at the coast. The impact of hurricane ‘Wilma’ in 2005 dominates the records, producing a super-elevation of the SWL above Mean Sea Level (MSL) of 1155 mm with an estimated return period of around 147 years. This paper explores the duality of increasing risks of oceanic inundation due to extreme events and increasing mean sea level over time, whilst also providing a range of recommendations for ensuring improved predictive model fitting and robustness of EVA for SWLs measured at tide gauges. When integrated with future IPCC AR6 sea level projections, the return level plots from the EVA provide decision makers with key guidance for design, strategic planning and climate change adaptation purposes at Key West, Florida.

show abstract

Section: Sensitivity Analysis Testing For Evasupporting

confidence: 88%

Section: The Shape Of the Eva Return Level Plotmentioning

confidence: 60%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Extreme Value Analysis of Ocean Still Water Levels along the USA East Coast—Case Study (Key West, Florida)

Watson

2023

Coasts

View full text Add to dashboard Cite

show abstract

“…Hosking (1990) compared the MoM against L‐Moments for samples of precipitation data in California and concluded that L‐moments outperforms the former. Later a similar comparison (Yılmaza et al., 2021) of ML and moment method against different types of L‐moment methods, best linear estimators (BLUE) and purely Bayesian MCMC methods, corroborates that L‐moments and Bayesian methods outperform the others in most cases. An additional benefit of the PWMs is the convenient way of statistical testing of the parameters for samples of size n by taking the case κ = 0 (i.e., data are asymptotically N (0, 0.5635/ n ) as the zero‐hypothesis, which must otherwise be rejected).…”

Section: Parameter Estimationmentioning

confidence: 62%

Toward a New Flood Assessment Paradigm: From Exceedance Probabilities to the Expected Maximum Floods and Damages

Todini,

Reggiani

2024

Water Resources Research

View full text Add to dashboard Cite

To assess flood risks, we seek to estimate the probability distribution of the worst possible single‐event over a contiguous period of N years rather than the cumulative losses expected over a planning horizon. For this we use the probability distribution FN of extreme flood events over a multi‐year period, which is different from using the conventional single‐valued exceedance probability of 1/N years. FN can be used to estimate the hazard and then proceed to the estimation of risk, which we define as the “largest expected damage” over the set period. It also allows for a more coherent determination of design values, which descend from fully acknowledging the aleatoric uncertainty of the underlying natural river flow process. The epistemic uncertainty is removed by marginalizing the aleatoric‐epistemic uncertainty joint distribution over the parameter space. The advantage of the proposed Bayesian approach, which can be summarized in 12 steps, is demonstrated for the 2021 River Ahr flood in Germany, which caused casualties and huge material damage. Adopting the multi‐year maxima extreme value distribution can potentially lead to the reclassification of vulnerability levels for flood‐prone areas and reconsideration of current policy‐making and flood risk communication.

show abstract

Editorial to the special issue: Recent statistical methods for data analysis, applied economics, business & finance

Göktaş

Akkuş

2021

Journal of Applied Statistics

View full text Add to dashboard Cite

Comparison of different estimation methods for extreme value distribution

Cited by 4 publications

References 40 publications

Extreme Value Analysis of Ocean Still Water Levels along the USA East Coast—Case Study (Key West, Florida)

Extreme Value Analysis of Ocean Still Water Levels along the USA East Coast—Case Study (Key West, Florida)

Toward a New Flood Assessment Paradigm: From Exceedance Probabilities to the Expected Maximum Floods and Damages

Editorial to the special issue: Recent statistical methods for data analysis, applied economics, business & finance

Contact Info

Product

Resources

About