ABSTRACT
The Wakeby distribution is analytically defined only in the inverse form. Therefore explicit expressions cannot be obtained for either the probability density function or the distribution function. The probability weighted moments method was used to estimate the parameters of the Wakeby distribution by Landwehr and Matalas. The choice of the estimating algorithm, which minimizes the root mean square error of the quantiles is shown to be unimportant when the upper flood quantiles are of interest and when the lower bound is unknown. This algorithm is based on probability weighted moments. These estimates were shown to be neither highly biased nor variable even for very small sample sizes. The Pareto distribution is the logical choice for modeling flood magnitudes that exceed a fixed threshold when it is reasonable to assume that successive floods follow a Poisson process and have independent magnitudes.
