Alpha稳定分布随机变量的产生

在实际应用中遇到的大量的非高斯信号或噪声具有显著的尖峰脉冲特性,其概率密度函数的衰减过程比高斯分布要慢,表现出显著的拖尾。而基于广义中心极限定理的Alpha稳定分布描述了信号统计分布的非高斯性和重拖尾性。实现服从Alpha稳定分布随机变量的仿真是开展相关研究的基础。该文由S2参数系下的分布模型的仿真算法导出标准参数系下Alpha稳定分布随机变量的仿真算法。并通过仿真实验证实了该仿真算法的可行性。

Generation of Random Variables Subject to the Alpha Stable Distribution

In practice,various non-gaussian signals and noises have distinct spiky and impulsive characteristics,the decay of its’probability density function is slower than the Gaussian distribution’s,showing significant tails.The Alpha stable distribution,which bases on the broad Central Limit Theorem,has the statistical characteristics of non-Gaussian and heavy tailed.The generation of random variables subject to the alpha stable distribution is the basis of related research.This paper gives the simulation algorithm of the Generation of random variables subject to the alpha stable distribution in the standard parameters derived from the algorithm in the S2parameters.Simulation experiments at the end of the paper verify the feasibility of the algorithm.