Open AccessON THE METHODOLOGY OF SELECTING DESIGN WAVE HEIGHT
Author(s) -
Yoshimi Goda
Publication year - 1988
Publication title -
proceedings of conference on coastal engineering/proceedings of ... conference on coastal engineering
Language(s) - English
Resource type - Journals
eISSN - 2156-1028
pISSN - 0589-087X
DOI - 10.9753/icce.v21.67
Subject(s) - weibull distribution , mathematics , statistics , monte carlo method , confidence interval , sample size determination , extreme value theory , range (aeronautics) , empirical distribution function , engineering , aerospace engineering
A statistically-rational method of extreme wave data analysis is presented. A combination of the Fisher-Tippett type I and the four Weibull distributions is proposed as the candidates of distribution functions. The least square method is used for data fitting. The best plotting position formula for each function is determined by the Monte Carlo method with 10,000 simulations per sample size. Confidence intervals of estimated extreme wave heights for given return periods are evaluated by simulations and expressed in the form of empirical formulas, for both the cases when the true distribution is known and unknown. An example of extreme wave data analysis is given.