Application of the generalized Pareto distribution to extreme value analysis in wind engineering

This paper discusses the generalized Pareto distribution (GPD) and its application to the statistical analysis of extreme wind speeds. Its main advantage is that it makes use of all relevant data on the high wind gusts produced by the storms of interest, not just the annual maxima, and it is not necessary to have a value for every year to carry out the analysis. The GPD is closely related to the generalized extreme value distribution (GEVD), and can be used to determine the appropriate value of shape factor, k, for use in the GEVD. However, a negative shape factor, corresponding to a Type II GEVD, is physically unrealistic, and should be avoided for long-term wind speed predictions. (C) 1999 Elsevier Science Ltd. All rights reserved.