Modélisation des erreurs pour le système de prévision PRÉVIS

2004 ◽  
Vol 31 (5) ◽  
pp. 892-897 ◽  
Author(s):  
Mario Lefebvre
Keyword(s):  
Statistical Models ◽  
Goodness Of Fit ◽  
Pareto Distribution ◽  
Laplace Distribution ◽  
Critical Threshold ◽  
Gaussian Distributions ◽  
Goodness Of Fit Tests ◽  
Generalized Pareto ◽  
Forecasting System

This paper examines models for the errors in forecasts of river and (or) watershed flows produced by the PREVIS forecasting system, which is used by Alcan, among other companies. We analyzed the following statistical models: generalized Pareto, Laplace, and Gaussian distributions, depending on the flow value forecasted by PREVIS. These models enable us to quantify the precision of the forecasts produced by PREVIS, as well as the risk of seeing the flow exceed a certain critical threshold, given the forecasted flow.Key words: modeling, Laplace distribution, Pareto distribution, goodness-of-fit tests, critical threshold.

scholarly journals Goodness-of-fit tests for Pareto distribution based on a characterization and their asymptotics

Statistics ◽  
2014 ◽  
Vol 49 (5) ◽  
pp. 1026-1041 ◽  
Author(s):  
Marko Obradović ◽  
Milan Jovanović ◽  
Bojana Milošević
Keyword(s):  
Goodness Of Fit ◽  
Pareto Distribution ◽  
Goodness Of Fit Tests

scholarly journals Maximum Likelihood Estimation for the Generalized Pareto Distribution and Goodness-of-Fit Test with Censored Data

2019 ◽  
Vol 17 (2) ◽  
Author(s):  
Minh H. Pham ◽  
Chris Tsokos ◽  
Bong-Jin Choi
Keyword(s):  
Maximum Likelihood ◽  
Maximum Likelihood Estimation ◽  
Censored Data ◽  
Goodness Of Fit ◽  
Pareto Distribution ◽  
Generalized Pareto Distribution ◽  
Likelihood Estimation ◽  
R Package ◽  
Goodness Of Fit Test ◽  
Generalized Pareto

The generalized Pareto distribution (GPD) is a flexible parametric model commonly used in financial modeling. Maximum likelihood estimation (MLE) of the GPD was proposed by Grimshaw (1993). Maximum likelihood estimation of the GPD for censored data is developed, and a goodness-of-fit test is constructed to verify an MLE algorithm in R and to support the model-validation step. The algorithms were composed in R. Grimshaw’s algorithm outperforms functions available in the R package ‘gPdtest’. A simulation study showed the MLE method for censored data and the goodness-of-fit test are both reliable.

scholarly journals Goodness of Fit Tests in Modeling the Distribution of the Daily Rate of Return of the WIG20 Companies

2012 ◽  
Vol 10 (2) ◽  
pp. 103-113
Author(s):  
Kamila Bednarz
Keyword(s):  
Goodness Of Fit ◽  
Laplace Distribution ◽  
Cumulative Distribution ◽  
Rate Of Return ◽  
Likelihood Method ◽  
Return Distribution ◽  
Chi Square ◽  
Goodness Of Fit Tests ◽  
Daily Rate ◽  
Chi Square Test

Goodness of Fit Tests in Modeling the Distribution of the Daily Rate of Return of the WIG20 Companies In this paper a classic rate of return was examined. Due to a limited quantitative range, the study included only the modeling of the rate of return distribution of the WIG20 index and its companies by means of the Laplace distribution and the Gaussian distribution. Additionally, the goodness of fit tests and methods of estimating the aforementioned distributions parameters were thoroughly covered. When applying the Laplace distribution to modeling the rate of return distribution the parameters were determined by means of two methods: the method of moments and the maximum likelihood method. The maximum period was determined, for which usefulness of the distribution in modeling the rates of return distribution was observed, as well as the results of the chi-square test for class intervals with varying length ensuring equal probability, and for intervals with identical length considering two methods of determining the theoretical size: in accordance with the cumulative distribution function as well as on the basis of the probability density function.

scholarly journals Maximum Likelihood Estimation for the Generalized Pareto Distribution and Goodness-of-Fit Test with Censored Data

2019 ◽  
Vol 17 (2) ◽  
Author(s):  
Maddalena Cavicchioli ◽  
Angeliki Papana ◽  
Ariadni Papana Dagiasis ◽  
Barbara Pistoresi
Keyword(s):  
Goodness Of Fit ◽  
Pareto Distribution ◽  
A Priori ◽  
Generalized Pareto Distribution ◽  
Likelihood Estimation ◽  
Large Database ◽  
Goodness Of Fit Test ◽  
Institutional Variables ◽  
Generalized Pareto ◽  
Selection Of

A non-parametric efficient statistical method, Random Forests, is implemented for the selection of the determinants of Central Bank Independence (CBI) among a large database of economic, political, and institutional variables for OECD countries. It permits ranking all the determinants based on their importance in respect to the CBI and does not impose a priori assumptions on potential nonlinear relationships in the data. Collinearity issues are resolved, because correlated variables can be simultaneously considered.

Sign in / Sign up

Export Citation Format

Share Document