Premium
ESTIMATING PARAMETERS OF EV1 DISTRIBUTION FOR FLOOD FREQUENCY ANALYSIS 1
Author(s) -
Jam Deepak,
Singh Vijay P.
Publication year - 1987
Publication title -
jawra journal of the american water resources association
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.957
H-Index - 105
eISSN - 1752-1688
pISSN - 1093-474X
DOI - 10.1111/j.1752-1688.1987.tb00784.x
Subject(s) - principle of maximum entropy , mathematics , statistics , maximum likelihood , method of moments (probability theory) , l moment , generalized method of moments , maximum likelihood sequence estimation , moment (physics) , least squares function approximation , entropy (arrow of time) , order statistic , panel data , physics , classical mechanics , quantum mechanics , estimator
The parameters of the extreme value type 1 distribution were estimated for 55 annual flood data sets by seven methods. These are the methods of (1) moments, (2) probability weighted moments, (3) mixed moments, (4) maximum likelihood estimation, (5) incomplete means, (6) principle of maximum entropy, and (7) least squares. The method of maximum likelihood estimation was found to be the best and the method of incomplete means the worst. The differences between the methods of principle of maximum entropy, probability weighted moments, moments, and least squares were only minor. The difference between these methods and the method of maximum likelihood was not pronounced.