A Novel Parameter Estimation Method of Alpha-stable Distribution Based on Extreme Value

摘要

Since Alpha-stable distribution was introduced as a generalization of Gaussian distribution, it has been applied to model and to analyze signals with high variability. After analyzing characteristic of PDF of Alpha-stable distribution, we propose a novel parameter estimation method of Alpha-stable distribution, based on asymptotic Pareto characteristic and asymmetry of its tails. Simulation and analysis results prove that this method could achieve much more accuracy and stability compared with other estimation methods.