This document compares 19 different distribution methods (Normal, LogNormal, etc.) based on their quantile estimates for various return periods (2, 5, 10, 25, 100 years) and the results of a Kolmogorov-Smirnov goodness-of-fit test. For most distribution methods, the quantile estimates increase with longer return periods as expected. The Kolmogorov-Smirnov test results show that for most distribution methods, the null hypothesis of the data fitting that distribution is accepted at significance levels of 1%, 5%, and 10%.
This document compares 19 different distribution methods (Normal, LogNormal, etc.) based on their quantile estimates for various return periods (2, 5, 10, 25, 100 years) and the results of a Kolmogorov-Smirnov goodness-of-fit test. For most distribution methods, the quantile estimates increase with longer return periods as expected. The Kolmogorov-Smirnov test results show that for most distribution methods, the null hypothesis of the data fitting that distribution is accepted at significance levels of 1%, 5%, and 10%.
This document compares 19 different distribution methods (Normal, LogNormal, etc.) based on their quantile estimates for various return periods (2, 5, 10, 25, 100 years) and the results of a Kolmogorov-Smirnov goodness-of-fit test. For most distribution methods, the quantile estimates increase with longer return periods as expected. The Kolmogorov-Smirnov test results show that for most distribution methods, the null hypothesis of the data fitting that distribution is accepted at significance levels of 1%, 5%, and 10%.