Minimum Sample Size Determination for Generalized Extreme Value Distribution

Abstract

Abstract\n Sample size determination is an important issue in statistical
\nanalysis. Obviously, the larger the sample size is, the better the
\nstatistical results we have. However, in many areas such as coastal
\nengineering and environmental sciences, it can be very expensive
\nor even impossible to collect large samples. In this paper, we
\npropose a general method for determining the minimum sample size
\nrequired by estimating the return levels from a generalized extreme
\nvalue distribution. Both simulation studies and the applications
\nto real data sets show that the method is easy to implement and the
\nresults obtained are very good.