Parameter Estimation for Generalized Extreme Value Distribution in Rainfall Forecasting: A Case Study of Bangkok

Autcha  Araveeporn; Paradorn  Sukpan

doi:10.6180/jase.202512_28(12).0009

Parameter Estimation for Generalized Extreme Value Distribution in Rainfall Forecasting: A Case Study of Bangkok

Autcha AraveepornThis email address is being protected from spambots. You need JavaScript enabled to view it. and Paradorn Sukpan

Department of Statistics, School of Science, King Mongkut’s Institute of Technology Ladkrabang, Bangkok, Thailand

Received: July 25, 2024
Accepted: February 6, 2025
Publication Date: April 16, 2025

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202512_28(12).0009

This study aims to compare efficiency methods for the estimated parameter of Generalized Extreme Value Distribution (GEVD), which consists of location, scale, and shape parameters. The parameter estimation employs the maximum likelihood (ML), generalized maximum likelihood (GML), Bayesian, and L-moments methods. The data is generated through simulation data in Gumbel, Fréchet, and Weibull distributions verified by shape parameters. The performance of these methods is evaluated using the minimum mean squared error (MSE) and mean absolute percentage error (MAPE). The results indicate that the Bayesian, ML, and GML methods consistently achieve the lowest MSE values, such as 0.0120 for location, 0.0066 for scale, and 0.005 for shape parameters when the sample size is 100 of the Gumbel distribution. In the real data application using 29 years of Bangkok rainfall data (1994-2023), the GEVD model estimated return levels for 2 to 9 years, with MAPEvalues ranging from 32.57% to 56.92% across different stations. The findings suggest that ML and GML methods outperform others in simulated and real-world applications. The proposed approach provides accurate and reliable forecasts of extreme rainfall, which are crucial for Bangkok’s urban planning and flood risk management.

Keywords: generalized extreme value distribution; generalized maximum likelihood; L-moments

[1] G.Casella and R. L. Berger. Statistical Inference. 2nd. California: The Wadsworth Group, 2001. Chap. 7.
[2] C.C.HolmsandS.G.Walker, (2003) “Statistical Inference with Exchangeability and Martingales" Philosophical Transactions of the Royal Society A 381: 1–17. DOI: 10.1098/rsta.2022.0143.
[3] J. Siebert, (2023) “Applications of Statistical Causal Inference in Software Engineering" Information and Software Technology 159: 1–34. DOI: 10.1016/j.infsof.2023.107198.
[4] T. T. Cal, Z. Gua, and R. Ma, (2023) “Statistical Inference for High-Dimensional Generalized Linear Models with Binary Outcomes" Journal of the American Sta tistical Association 118: 1319–1332. DOI: 10.1080/01621459.2021.1990769.
[5] C.H.Chong, M.Hoffmann, Y. Liu, M. Rosenbaum, and G. Szymanski, (2024) “Statistical Inference for Rough Volatility: Central Limit Theorems" The Annals of Applied Probability 34: 2600–2649. DOI: 10.1214/ 23-AAP2002.
[6] J. L. Wadsworth and R. Campbell, (2024) “Statistical Inference for Multivariate Extremes via a Geometric Approach" Journal of the Royal Statistical Society Series B: Statistical Methodology 86: 1243–1265. DOI: 10.1093/jrsssb/qkae030.
[7] P. C. Bellec and C.-H. Zhang, (2023) “Debiasing Con vex Regularized Estimators and Interval Estimation in Linear Models" The Annals of Statistics 51: 391–436. DOI: 10.1214/22-AOS2243.
[8] C.Shi, J. Zhu, Y. Shen, S. Luo, H. Zhu, and R. Song, (2024) “Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process" Journal of the American Statistical Association 119: 273–284. DOI: 10.1080/01621459.2022.2110878.
[9] S. F. Cheung, I. J. Agaloos Pesigan, and W. N. Vong, (2023) “DIY Bootstrapping: Getting the Nonparametric Bootstrap Confidence Interval in SPSS for any Statistics or Function of Statistics" Behavior Research Methods 55: 474–490. DOI: 10.3758/s13428-022-01808-5.
[10] L.MakkonenandM.Tikanmaki,(2019)“AnImproved Method of Extreme Value Analysis" Journal of Hydrology 2: 1–7. DOI: 10.1016/j.hydroa.2018.100012.
[11] H.Tabari, (2021) “Extreme Value Analysis Dilemma for Climate Change Impact Assessment on Global Flood and Extreme Precipitation" Journal of Hydrology 593: 1 56. DOI: 10.1016/j.jhydrol.2020.125932.
[12] R.Raiman, S.Sukono, S.Supian, and N.Ismail,(2021) “Analysing the Decision Making for Agricultural Risk Assessment: An Application of Extreme Value Theory" Decision Science Letters 10: 351–360. DOI: 10.5267/j.dsl.2021.2.003.
[13] F. D. Paola, M. Giugni, F. Pugliese, A. Annis, and F. Nardi, (2018) “GEV Parameter Estimation and Stationary vs. Non-Stationary Analysis of Extreme Rain fall in African Test Cities" Hydrology 5: 1–23. DOI: 10.3390/hydrology5020028.
[14] S. Yoon, W. Cho, J.-H. Heo, and C. E. Kim, (2010) “A Full Bayesian Approach to Generalized Maximum Likelihood Estimation of Generalized Extreme Value Distribution" Stochastic Environmental Research and Risk Assessment 24: 761–770. DOI: 10.1007/s00477-009 0362-7.
[15] A. Shabri, U. N. Ahmad, and Z. A. Zakaria, (2011) “TL-Moments and L-Moments Estimation of the Generalized Logistic Distribution" Journal of Mathematics Research 3: 97–106. DOI: 10.5539/jmr.v3n1p97.
[16] S. B. Habeeb, F. K. Abdullah, R. N. Shalan, A. S. Hassan, E. M. Almetwally, F. M. Alghamdi, S. M. Ahmed Alsheikh, and M.Hossain,(2024)“Comparisonof Some Bayesian Estimation Methods for Type-I Generalized Ex treme Value Distribution with Simulation" Alexandria Engineering Journal 98: 356–363. DOI: 10.1016/j.aej.2024.04.042.
[17] Y. Ali, S. Washington, and M. Haque, (2023) “Estimating Real-Time Crash Risk at Signalized Intersections: A Bayesian Generalized Extreme Value Approach" Safety Science 164: 1–9. DOI: 10.1016/j.ssci.2023.106181.
[18] A.Louzaoui and M.E.Arrouchi,(2020) “On the Maximum Likelihood Estimation of Extreme Value Index Based on k-Record Values" Journal of Probability and Statis tics 2020: 1–9. DOI: 10.1155/2020/5497413.
[19] S. E. Adlouni, T. B. Ouarda, X. Zhang, R. Roy, and B. Bobée, (2007) “Generalized Maximum Likelihood Estimators for the Nonstationary Generalized Extreme Value Model" Water Resources Research 43(3): 1–14. DOI: 10.1029/2005WR004545.
[20] F. Krüger, S. Lerch, T. Thorarinsdottir, and T. Gneiting, (2021) “Predictive Inference based on Markov Chain MonteCarloOutput "International Statistical Review 89: 274–301. DOI: 10.1111/insr.12405.
[21] S. A. Khan, I. Hussain, T. Hussain, F. Muhammad, Y. S. Muhammad, and A. M. Shoukry, (2017) “Re gional Frequency Analysis of Extremes Precipitation us ing L-Moments and Partial L- moments" Advances in Meteorology 2017: 1–20. DOI: 10.1155/2017/6954902.
[22] E. Tanprayoon, U. Tonggumnead, and S. Aryuyuen, (2023) “New Extension of Generalized Extreme Value Distribution: Extreme Value Analysis and Return Level Estimation of the Rainfall Data" Trends in Sciences 20: 1–13. DOI: 10.48048/tis.2023.4034.
[23] E. S. Martins and J. R. Stedinger, (2000) “Generalized Maximum-Likelihood Generalized Extreme-Value Quan tile Estimators for Hydrologic Data" Water Resources Research 36: 737–744. DOI: 10.1029/1999WR900330.
[24] J. L. Ng, K. H. Chan, N. I. F. Noh, R. Razman, S. Surol, J. C. Lee, and R. A. Al-Mansob, (2022) “Statistical Modelling of Extreme Temperature in Peninsular Malaysia" IOP Conference Series: Earth and Environmental Science 1022: 1–9. DOI: 10.1088/1755-1315/1022/1/012072.
[25] S. Coles. An Introduction to Statistical Modeling of Ex treme Values. London: Springer, 2001. Chap. 1.
[26] J. Beirlant, Y. Goegebeur, J. Teugels, and J. Segers. Statistics of Extremes: Theory and Applications. New York: John Wiley & Sons, 2004. Chap. 1.
[27] J. Nocedal and S. J. Wright. Numerical Optimization. 2nd. New York: Springer, 1999. Chap. 1.
[28] E. Greenshtein and Y. Ritov, (2022) “Generalized Maxi mumLikelihood Estimation of the Mean of Parameters of Mixtures, with Applications to Sampling and to Observational Studies" Electronic Journal of Statistics 16: 5934–5954. DOI: 10.1214/22-EJS2082.
[29] S. Brooks, (2002) “Markov Chain Monte Carlo Method and its Application" Journal of the Royal Statistical Society: Series D (the Statistician) 47: 69–100. DOI: 10.1111/1467-9884.00117.
[30] S. Chib and E. Greenberg, (1995) “Understanding the Metropolis-Hastings Algorithm" The American Statis tician 49(4): 327–335. DOI: 10.1080/00031305.1995.10476177.
[31] A. Gelman, J. B. Carlin, H. S. Stern, D. B. Dunson, A. Vehtari, and D. B. Rubin. Bayesian Data Analysis. 3rd. Florida: CRC Press Taylor & Francis Group, 2013. Chap. 2.
[32] A.Gelman and D.B.Rubin,(1992)“Inferencefrom Iter ative Simulation Using Multiple Sequences" Statistical Science 7: 457–472. DOI: 10.1214/ss/1177011136.
[33] J.R.M.Hosking,(1990) “L-moments: Analysis and Estimation Distributions using Linear Combinations of Order Statistics" Journal of the Royal Statistical Society Series B: Statistical 52: 105–124. DOI: 10.1111/j.2517-6161.1990.tb01775.x.
[34] E. A. H. Elamir and A. H. Seheult, (2004) “Exact Vari ance Structure of Sample L-moments" Journal of Sta tistical Planning and Inference 124: 337–359. DOI: 10.1016/S0378-3758(03)00213-1.
[35] J. Karvanen, (2006) “Estimation of Quantile Mixtures via L-Moments and Trimmed L-moments" Computa tional Statistics & Data Analysis 51: 947–959. DOI: 10.1016/j.csda.2005.09.014.
[36] E. Gilland and R. W. Katz, (2016) “extRems 2.0: An Extreme Value Analysis Package in R" Journal of Sta tistical Software 72: 1–39. DOI: https://doi.org/10.18637/jss.v072.i08.
[37] D. A. Dickey and W. A. Fuller, (1979) “Distribution of the Estimators for Autoregressive Time Series with a Unit Root" Journal of the American Statistical As sociation 74: 427–431. DOI: 10.1080/01621459.1979.10482531.
[38] R. M. Hirsch, J. R. Slack, and R. A. Smith, (1982) “Techniques of Trend Analysis for Monthly Water Quality Data" Water Resources Research 18: 107–121. DOI: 10.1029/WR018i001p00107.
[39] T. R. Ferreira, G. R. Liska, and L. A. Beijo, (2024) “As sessment of Alternative Methods for Analysing Maximum Rainfall Spatial Data based on Generalized Extreme Value Distribution" Discover Applied Science 6: 1–21. DOI: https://doi.org/10.1007/s42452-024-05685-9.
[40] Z. Jiao, A. Alam, J. Yuan, C. Farnham, and K. Emura, (2024) “Prediction of Extreme Rainfall Events in 21st Century- The results Based on Bayesian Markov Chain Monte Carlo" Urban Climate 53: 1–13. DOI: 10.1016/j.uclim.2024.101822.
[41] S. H. Lee and S. J. Maeng, (2005) “Estimating of Drought Rainfall using L-Moments" Irrigation and Drainage 54: 279–294. DOI: 10.1002/ird.178.
[42] T. Prahadchai, Y. Shin, P. Busababodhin, and J.-S. Park, (2023) “Analysis of Maximum Precipitation in Thailand using Non-Stationary Extreme Value Models" Atmospheric Science Letters 24: 1–11. DOI: 10.1002/asl.1145.
[43] R. Choudury and T. D. Roy, (2024) “Rainfall Analy sis of Guwahati City using the Method of L-Moments, Tl-Moments & Maximum Likelihood Estimation" International Journal of Scientific Research in Multidisciplinary Studies 10: 19–25. DOI: 10.26438/ijsrms/v10i5.1925.
[44] I. Christos, P. Galiatsatou, V. Glenis, P. Prinos, and C. Kilsby, (2023) “Urban Flood Modelling under Extreme Rainfall Conditions for Building-Level Flood Exposure Analysis" Hydrology 10: 1–19. DOI: 10.3390/hydrology10080172.