Modelagem estocástica usando a distribuição generalizada de valores extremos e momentos LH: uma abordagem via software livre R

Wagner Alessandro  Pansera; Bendito Martins Gomes

doi:10.35819/remat2021v7i2id5106

Authors

Wagner Alessandro Pansera Universidade Tecnológica Federal do Paraná (UTFPR), Departamento de Engenharia Civil, Toledo, PR, Brasil https://orcid.org/0000-0002-6850-6775
Bendito Martins Gomes Universidade Estadual do Oeste do Paraná (UNIOESTE), Programa de Pós-Graduação em Engenharia Agrícola, Cascavel, PR, Brasil https://orcid.org/0000-0003-0223-4049

DOI:

https://doi.org/10.35819/remat2021v7i2id5106

Keywords:

GEV, extreme values, free software R, stochastic modeling

Abstract

Generalized Extreme Value (GEV) distribution is used to modeling extreme natural events, such as rainfall, floods, wind speed and temperature. An important issue for GEV use is the choice of parameter estimation methodology. The commonly used methodologies are maximum likelihood and conventional moments. However, studies indicate that such methodologies do not always produce a reliable estimate of GEV parameters. In this sense, it is interesting to use LH moments, as they better characterize the upper tail of the distribution due to the emphasis given to the highest observed values. Nevertheless, there are no computational routines developed for GEV use combined with LH moments in free software. Therefore, this research aimed at developing a computational routine in free software R for stochastic modeling through GEV, using LH moments to estimate its parameters and verify goodness-of-fit. Maximum annual flow data available in the literature was used to demonstrate the applicability of the computational routine. This research contributes to disseminate the use of LH moments and facilitate stochastic modeling of extreme environmental events.

Downloads

Download data is not yet available.

Author Biographies

Wagner Alessandro Pansera, Universidade Tecnológica Federal do Paraná (UTFPR), Departamento de Engenharia Civil, Toledo, PR, Brasil

http://lattes.cnpq.br/9083466536550741
Bendito Martins Gomes, Universidade Estadual do Oeste do Paraná (UNIOESTE), Programa de Pós-Graduação em Engenharia Agrícola, Cascavel, PR, Brasil

http://lattes.cnpq.br/4355317240921602

References

ABU EL-MAGD, N. A. T. TL-moments of the exponentiated generalized extreme value distribution. Journal of Advanced Research, v. 1, n. 4, p. 351-359, 2010. DOI: https://doi.org/10.1016/j.jare.2010.06.003.

COLES, S. An introduction to statistical modeling of extreme values. London: Springer, 2001. 209 p.

GILLELAND, E.; RIBATET, M.; STEPHENSON, A. G. A software review for extreme value analysis. Extremes, v. 16, n. 1, p. 103-119, 2013. DOI: https://doi.org/10.1007/s10687-012-0155-0.

HOSKING, J. R. M. L-Moments: Analysis and Estimation of Distributions Using Linear Combinations of Order Statistics. Journal of the Royal Statistical Society: Series B (Methodological), v. 52, n. 1, p. 105-124, 1990. Disponível em: https://www.jstor.org/stable/2345653. Acesso em: 9 ago. 2021.

HOSKING, J. R. M.; WALLIS, J. R.; WOOD, E. F. Estimation of the Generalized Extreme-Value Distribution by the Method of Probability-Weighted Moments. Technometrics, v. 27, n. 3, p. 251-261, 1985. DOI: https://doi.org/10.1080/00401706.1985.10488049.

JENKINSON, A. F. The frequency distribution of the annual maximum (or minimum) values of meteorological elements. Quarterly Journal of the Royal Meteorological Society, v. 81, n. 348, p. 158-171, abr. 1955. DOI: https://doi.org/10.1002/qj.49708134804.

KATZ, R. W.; PARLANGE, M. B.; NAVEAU, P. Statistics of extremes in hydrology. Advances in Water Resources, v. 25, n. 8-12, p. 1287-1304, ago./dez. 2002. DOI: https://doi.org/10.1016/S0309-1708(02)00056-8.

MARTINS, E. S.; STEDINGER, J. R. Generalized maximum-likelihood generalized extreme-value quantile estimators for hydrologic data. Water Resources Research, v. 36, n. 3, p. 737-744, 1 mar. 2000. DOI: https://doi.org/10.1029/1999WR900330.

NAGHETTINI, M.; PINTO, E. J. A. Hidrologia estatística. Belo Horizonte: CPRM. 2007. 552 p.

PANSERA, W. A. Distribuição generalizada de chuvas máximas no Estado do Paraná. Orientador: Benedito Martins Gomes. Coorientadores: Marcio Antonio Vilas Boas e Miguel Angel Uribe-Opazo. 2013. 94 f. Tese (Doutorado em Engenharia Agrícola) - Programa de Pós-Graduação em Engenharia Agrícola, Universidade Estadual do Oeste do Paraná, Cascavel, 2013. Disponível em: http://tede.unioeste.br/handle/tede/2626. Acesso em: 9 ago. 2021.

QUEIROZ, M. M. F.; CHAUDHRY, F. H. Analysis of extreme hydrological events using GEV distribution and LH moments. Revista Brasileira de Engenharia Agrícola e Ambiental, v. 10, n. 2, p. 381-389, 2006. DOI: https://doi.org/10.1590/S1415-43662006000200020.

R CORE TEAM. R: A language and environment for statistical computing. Vienna: R Foundation for Statistical Computing, 2021. Disponível em: http://www.R-project.org. Acesso em: 27 abr. 2021.

RAO, A. R.; HAMED, K. H. Flood Frequency Analysis. Boca Raton, Flórida: CRC Press, 2000. 350 p.

WANG, Q. J. Approximate goodness-of-fit tests of fitted generalized extreme value distributions using LH moments. Water Resources Research, v. 34, n. 12, p. 3497-3502, 1 dez. 1998. DOI: https://doi.org/10.1029/98WR02364.

WANG, Q. J. LH moments for statistical analysis of extreme events. Water Resources Research, v. 33, n. 12, p. 2841-2848, 1997. Disponível em: https://agupubs.onlinelibrary.wiley.com/doi/pdf/10.1029/97WR02134. Acesso em: 9 ago. 2021.

WICKHAM, Hadley. Advanced R. Boca Raton, Florida: CRC, 2015. 456 p.