Parameter estimation based on partial l-Moments method for censored samples

Abstract

Estimation of flood magnitude is a crucial component in planning, designing, and managing of water resources projects. The main focus in hydrologic design is the estimation of high flow quantile. L-moments, popular among hydrologist in flood estimation is known to be oversensitive towards the lower part of the distribution and gives insufficient weight to large sample values. As an alternative, the method of partial L-moments (PL-moments) is proposed to give weightage to the upper part of distribution and large values in censored sample. In this paper, three widely used distributions are selected namely; generalized extreme value (GEV), generalized logistic (GLO) and generalized Pareto (GPA) distribution, for the analysis of censored flood samples. Monte Carlo simulations are conducted to illustrate the performance of PL-moments compared to simple L-moments in fitting each distribution to its samples. Finally, both simple L-moments and PL-moments are used to fit the GLO distribution to two data sets of annual maximum flow series of River Ketil in Kedah and River Gemencheh in Negeri Sembilan, Malaysia.