Parameter Estimation of Approximated Generalized Least Squares Estimators for the Generalized Pareto Distribution

The generalized Pareto distribution (GPD) is one of the most important distribution in statistics analysis.This paper is based on sample quantiles of the GPD.First,the shape parameter estimator that has high estimated precision is solved,then the approximated generalized least squares estimation expressions of the location and scale parameters are obtained for the GPD.The proposed method is easy and has no limitation for the shape parameter.In addition,it has high estimation accuracy under Monte-Carlo simulation tests.