论文部分内容阅读
Oliver于1993年提出的K分布形状参数的V-估计器(VE),虽然具有免于求解非线性方程的计算因而估计效率高的优点,但是,其估计精度却低于许多其他矩估计器的估计精度,且有时会出现奇异值的情况.为扬长避短,在对V-估计器的估计偏差进行推导和分析的基础上,通过一系列Monte-Carlo实验,V-估计器改进成本文提出的具有校正项的V-估计器(VCE).VCE克服了V-估计器的上述缺点.仿真实验表明,VCE的估计精度不但显著优于VE,而且在效率和精度上都优于通常被认为是精度最高的矩估计器中的U-估计器.特别是,实验结果显示,VCE更适合于小样本长度下的情况,这个特点使得它更便于实际应用.
The V-estimator (VE) of K distribution shape parameters proposed by Oliver in 1993 has the advantage of high efficiency and high efficiency without the calculation of nonlinear equations. However, its estimation accuracy is lower than that of many other moment estimators Estimation accuracy, and sometimes the case of singular value.In order to avoid weaknesses, based on the derivation and analysis of the estimated bias of the V-estimator, through a series of Monte-Carlo experiments, the V- The VCE estimator (VCE) of the correction term VCE overcomes the above shortcomings of the V-estimator.The simulation results show that the VCE estimation accuracy is not only better than VE, but also superior in efficiency and accuracy over what is usually considered as accuracy U-estimator in the highest Moment estimator In particular, the experimental results show that the VCE is more suitable for small sample lengths, a feature that makes it more practical.