The accuracy of design values predicted from extreme value analysis

This paper reports a study of predicted values of the 1 : 50 yr windspeed p roduced by four different methods of extreme value analysis. The methods us ed were the obsolete Classical Gumbel method; Gumbel-Lieblein BLUE; the Mod ified Gumbel method and the Method of Independent Storms. For each method, synthetic wind records were generated consisting of 100 storm maxima for ea ch year and for a duration of 10(10)50 years. The parent distribution was c hosen so that q = V-2 had an exponential probability distribution. For each method tested, 10 000 data sets were analysed and the slope and intercept parameters were used to predict a Value of q(50) for each set. The 10 000 r ealisations of q50 were then examined for bias and statistical variation ab out the (known) theoretical value. The tests indicate that where sufficient ly continuous data is available, the Method of Independent Storms should be used. Otherwise if only annual maxima are available, Gumbel-Lieblein BLUE gives the best results for small data sets, but Modified Gumbel is an accep table alternative, particularly for samples N > 25. (C) 2001 Elsevier Scien ce Ltd. All rights reserved.