进化策略在极大似然法参数估计中的应用

采用极大似然法进行参数估计,是为了避免传统优化算法的缺点。本文采用进化策略算法与极大似然参数估计法相结合使参数估计变量不再受初始值影响,从而可获得全局更优的解。最后,以威布尔三参数分布为例进行参数估计。结果表明,该方法有求解精度高和收敛速度快的优点,从而使进化策略算法能更好地应用于数理统计中。

Evolution Strategies in the Parameter Estimation of the Maximum Likelihood Method

Using the maximum likelihood method to carry on parameter estimation is to avoid the traditional optimization algorithms'shortcomings.This article uses the evolutional strategy algorithm and the maximum likelihood parameter estimation method for parameter estimation not to be affected by the initial value,but obtain a globally optimal solution.Finally parameter estimation is carried out based on the Weibulls'three parameter distribution.The results indicate this method has the merits of high solution precision and fast convergence speed,and the evolution strategy algorithm can be better applied in mathematical statistics.