Open AccessStudy of Various Techniques for Estimating the Generalised Extreme Value Distribution Parameters
Author(s) -
Iqbal Hossain,
Monzur Alam Imteaz,
Anirban Khastagir
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1067/1/012065
Subject(s) - extreme value theory , maximum likelihood , statistics , estimation , generalized extreme value distribution , method of moments (probability theory) , mathematics , series (stratigraphy) , estimation theory , econometrics , engineering , paleontology , systems engineering , estimator , biology
Generalised extreme value distribution (GEVD) remains the commonly employed technique for investigating the probability of occurrence of extreme events for given recurrence of intervals. However, the application of the GEV distribution requires the estimation of its three parameters. There are different methods presented in the literature to determine the parameters of the GEVD. Different methods have been adopted by different researchers in determining the three parameters. This paper investigates the comparison of the commonly used methods to estimate the GEVD parameters. The maximum likelihood estimation (MLE), generalised maximum likelihood estimation (GMLE) and L-moments methods were considered in this study. The analysis was performed using the monthly extreme rainfall of Tasmania, Australia. The GEVD was fitted to four different data sets using the three parameters estimation techniques. The outcomes of the analysis suggest that parameters estimation techniques have negligible impact on the magnitude of the parameters. However, length of the data series has minor impact on the parameters value of different parameters estimation techniques.