scholarly journals A multiple threshold method for fitting the generalized Pareto distribution and a simple representation of the rainfall process

2010 ◽  
Vol 7 (4) ◽  
pp. 4957-4994 ◽  
Author(s):  
R. Deidda
Keyword(s):  
Time Series ◽  
Distribution Function ◽  
Pareto Distribution ◽  
Generalized Pareto Distribution ◽  
Daily Rainfall ◽  
Rainfall Time Series ◽  
Threshold Method ◽  
Generalized Pareto ◽  
Multiple Threshold ◽  
Optimum Threshold

Abstract. Previous studies indicate the generalized Pareto distribution (GPD) as a suitable distribution function to reliably describe the exceedances of daily rainfall records above a proper optimum threshold, which should be selected as small as possible to retain the largest sample while assuring an acceptable fitting. Such an optimum threshold may differ from site to site, affecting consequently not only the GPD scale parameter, but also the probability of threshold exceedance. Thus a first objective of this paper is to derive some expressions to parameterize a simple threshold-invariant three-parameter distribution function which is able to describe zero and non zero values of rainfall time series by assuring a perfect overlapping with the GPD fitted on the exceedances of any threshold larger than the optimum one. Since the proposed distribution does not depend on the local thresholds adopted for fitting the GPD, it will only reflect the on-site climatic signature and thus appears particularly suitable for hydrological applications and regional analyses. A second objective is to develop and test the Multiple Threshold Method (MTM) to infer the parameters of interest on the exceedances of a wide range of thresholds using again the concept of parameters threshold-invariance. We show the ability of the MTM in fitting historical daily rainfall time series recorded with different resolutions. Finally, we prove the supremacy of the MTM fit against the standard single threshold fit, often adopted for partial duration series, by evaluating and comparing the performances on Monte Carlo samples drawn by GPDs with different shape and scale parameters and different discretizations.

scholarly journals A multiple threshold method for fitting the generalized Pareto distribution to rainfall time series

2010 ◽  
Vol 14 (12) ◽  
pp. 2559-2575 ◽  
Author(s):  
R. Deidda
Keyword(s):  
Time Series ◽  
Distribution Function ◽  
Pareto Distribution ◽  
Generalized Pareto Distribution ◽  
Daily Rainfall ◽  
Rainfall Time Series ◽  
Threshold Method ◽  
Generalized Pareto ◽  
Multiple Threshold ◽  
Optimum Threshold

Abstract. Previous studies indicate the generalized Pareto distribution (GPD) as a suitable distribution function to reliably describe the exceedances of daily rainfall records above a proper optimum threshold, which should be selected as small as possible to retain the largest sample while assuring an acceptable fitting. Such an optimum threshold may differ from site to site, affecting consequently not only the GPD scale parameter, but also the probability of threshold exceedance. Thus a first objective of this paper is to derive some expressions to parameterize a simple threshold-invariant three-parameter distribution function which assures a perfect overlapping with the GPD fitted on the exceedances over any threshold larger than the optimum one. Since the proposed distribution does not depend on the local thresholds adopted for fitting the GPD, it is expected to reflect the on-site climatic signature and thus appears particularly suitable for hydrological applications and regional analyses. A second objective is to develop and test the Multiple Threshold Method (MTM) to infer the parameters of interest by using exceedances over a wide range of thresholds applying again the concept of parameters threshold-invariance. We show the ability of the MTM in fitting historical daily rainfall time series recorded with different resolutions and with a significative percentage of heavily quantized data. Finally, we prove the supremacy of the MTM fit against the standard single threshold fit, often adopted for partial duration series, by evaluating and comparing the performances on Monte Carlo samples drawn by GPDs with different shape and scale parameters and different discretizations.

Rate of convergence for the generalized Pareto approximation of the excesses

2003 ◽  
Vol 35 (04) ◽  
pp. 1007-1027 ◽  
Author(s):  
J.-P. Raoult ◽  
R. Worms
Keyword(s):  
Distribution Function ◽  
Uniform Convergence ◽  
Rate Of Convergence ◽  
Pareto Distribution ◽  
Generalized Pareto Distribution ◽  
Domain Of Attraction ◽  
Extreme Value Distribution ◽  
Extreme Value ◽  
Value Distribution ◽  
Generalized Pareto

Let F be a distribution function in the domain of attraction of an extreme-value distribution H γ. If F u is the distribution function of the excesses over u and G γ the distribution function of the generalized Pareto distribution, then it is well known that F u (x) converges to G γ(x/σ(u)) as u tends to the end point of F, where σ is an appropriate normalizing function. We study the rate of (uniform) convergence to 0 of F̅ u (x)-G̅γ((x+u-α(u))/σ(u)), where α and σ are two appropriate normalizing functions.

scholarly journals Introduction to Extreme Seeking Entropy

Entropy ◽  
2020 ◽  
Vol 22 (1) ◽  
pp. 93 ◽  
Author(s):  
Jan Vrba ◽  
Jan Mareš
Keyword(s):  
Time Series ◽  
Real Time ◽  
Adaptive Filters ◽  
Pareto Distribution ◽  
Adaptive System ◽  
Learning Algorithms ◽  
Synthetic Data ◽  
Generalized Pareto Distribution ◽  
Multi Scale ◽  
Generalized Pareto

Recently, the concept of evaluating an unusually large learning effort of an adaptive system to detect novelties in the observed data was introduced. The present paper introduces a new measure of the learning effort of an adaptive system. The proposed method also uses adaptable parameters. Instead of a multi-scale enhanced approach, the generalized Pareto distribution is employed to estimate the probability of unusual updates, as well as for detecting novelties. This measure was successfully tested in various scenarios with (i) synthetic data, (ii) real time series datasets, and multiple adaptive filters and learning algorithms. The results of these experiments are presented.

Improving daily rainfall extremes simulation using the generalized Pareto distribution: a case study in Western Iran

2022 ◽  
Vol 85 ◽  
pp. 193-204
Author(s):  
N Shahraki ◽  
S Marofi ◽  
S Ghazanfari
Keyword(s):  
Spatial Correlation ◽  
Water Resource ◽  
Pareto Distribution ◽  
Generalized Pareto Distribution ◽  
Daily Rainfall ◽  
Information Criterion ◽  
Rainfall Simulation ◽  
Model Order ◽  
Generalized Pareto ◽  
Agricultural Planning

Prediction of the occurrence or non-occurrence of daily rainfall plays a significant role in agricultural planning and water resource management projects. In this study, gamma distribution function (GDF), kernel, and exponential (EXP) distributions were coupled (piecewise) with a generalized Pareto distribution. Thus, the gamma-generalized Pareto (GGP), kernel-generalized Pareto (KGP), and exponential-generalized Pareto (EGP) models were used. The aim of the present study was to introduce new methods to modify the simulated generation of extreme rainfall amounts of rainy seasons based on the preserved spatial correlation. The best approach was identified using the normalized root mean square error (NRMSE) criterion. For this purpose, the 30-yr daily rainfall datasets of 21 synoptic weather stations located in different climates of West Iran were analyzed. The first, second, and third-order Markov chain (MC) models were used to describe rainfall time series frequencies. The best MC model order was detected using the Akaike information criterion and Bayesian information criterion. Based on the best identified MC model order, the best piecewise distribution models, and the Wilks approach, rainfall events were modeled with regard to the spatial correlation among the study stations. The performance of the Wilks approach was verified using the coefficient of determination. The daily rainfall simulation resulted in a good agreement between the observed and the generated rainfall data. Hence, the proposed approach is capable of helping water resource managers in different contexts of agricultural planning.

scholarly journals Bayesian trend analysis for daily rainfall series of Barcelona

2010 ◽  
Vol 26 ◽  
pp. 71-76 ◽  
Author(s):  
M. I. Ortego ◽  
J. Gibergans-Báguena ◽  
R. Tolosana-Delgado ◽  
J. J. Egozcue ◽  
M. C. Llasat
Keyword(s):  
Climate Change ◽  
Climate Change Scenario ◽  
Pareto Distribution ◽  
Generalized Pareto Distribution ◽  
Daily Rainfall ◽  
Change Scenario ◽  
Generalized Pareto ◽  
Abrupt Changes ◽  
Physical Features ◽  
Threshold Approach

Abstract. A Point-Over-Threshold approach using a reparameterization of the Generalized Pareto Distribution (GPD) has been used to assess changes in the daily rainfall Barcelona series (1854–2006). A Bayesian approach, considering the suitable scale and physical features of the phenomenon, has been used to look for these alterations. Two different models have been assessed: existence of abrupt changes in the new GPD parameters due to modifications of the observatory locations and trends in these GPD parameters, pointing to a climate change scenario.

scholarly journals EXPECTED SHORTFALL DENGAN PENDEKATAN GLOSTEN-JAGANNATHAN-RUNKLE GARCH DAN GENERALIZED PARETO DISTRIBUTION

2020 ◽  
Vol 9 (4) ◽  
pp. 505-514
Author(s):  
Lina Tanasya ◽  
Di Asih I Maruddani ◽  
Tarno Tarno
Keyword(s):  
Time Series ◽  
Stock Return ◽  
Pareto Distribution ◽  
Generalized Pareto Distribution ◽  
Garch Model ◽  
Value Theory ◽  
Expected Shortfall ◽  
Series Data ◽  
Generalized Pareto ◽  
Heavy Tailed

Stock is a type of investment in financial assets that are many interested by investors. When investing, investors must calculate the expected return on stocks and notice risks that will occur. There are several methods can be used to measure the level of risk one of which is Value at Risk (VaR), but these method often doesn’t fulfill coherence as a risk measure because it doesn’t fulfill the nature of subadditivity. Therefore, the Expected Shortfall (ES) method is used to accommodate these weakness. Stock return data is time series data which has heteroscedasticity and heavy tailed, so time series models used to overcome the problem of heteroscedasticity is GARCH, while the theory for analyzing heavy tailed is Extreme Value Theory (EVT). In this study, there is also a leverage effect so used the asymmetric GARCH model with Glosten-Jagannathan-Runkle GARCH (GJR-GARCH) model and the EVT theory with Generalized Pareto Distribution (GPD) to calculate ES of the stock return from PT. Bank Central Asia Tbk for the period May 1, 2012-January 31, 2020. The best model chosen was ARIMA(1,0,1) GJR-GARCH(1,2). At the 95% confidence level, the risk obtained by investors using a combination of GJR-GARCH and GPD calculations for the next day is 0.7147% exceeding the VaR value of 0.6925%. 

Rate of convergence for the generalized Pareto approximation of the excesses

2003 ◽  
Vol 35 (4) ◽  
pp. 1007-1027 ◽  
Author(s):  
J.-P. Raoult ◽  
R. Worms
Keyword(s):  
Distribution Function ◽  
Uniform Convergence ◽  
Rate Of Convergence ◽  
Pareto Distribution ◽  
Generalized Pareto Distribution ◽  
Domain Of Attraction ◽  
Extreme Value Distribution ◽  
Extreme Value ◽  
Value Distribution ◽  
Generalized Pareto

Let F be a distribution function in the domain of attraction of an extreme-value distribution Hγ. If Fu is the distribution function of the excesses over u and Gγ the distribution function of the generalized Pareto distribution, then it is well known that Fu(x) converges to Gγ(x/σ(u)) as u tends to the end point of F, where σ is an appropriate normalizing function. We study the rate of (uniform) convergence to 0 of F̅u(x)-G̅γ((x+u-α(u))/σ(u)), where α and σ are two appropriate normalizing functions.

Sign in / Sign up

Export Citation Format

Share Document