Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (7): 36-37.

• 学术探讨 • Previous Articles     Next Articles

Estimation of exponentiated weibull distribution parameters using a fuzzy least-squares

  

  • Received:2006-07-07 Revised:1900-01-01 Online:2007-03-01 Published:2007-03-01

指数威布尔分布参数的模糊最小二乘估计

田艳芳 师义民 李凤   

  1. 西北工业大学
  • 通讯作者: 田艳芳

Abstract: The purpose of this paper is to find a robust estimation method for a two-parameter exponentiated weibull distribution when outliers are present. when the outliers are present, a cluster-wise fuzzy least-squares is used. least-squares and weighted least-squares for parameters is obtained under the complete data. Numerical comparisons between these methods are implemented. According to these comparisons, it is suggested that fuzzy least-squares method is preferable.

摘要: 本文讨论了指数威布尔分布参数的估计问题。当寿命数据含有异常数据时,利用基于模糊聚类的最小二乘方法对参数进行估计,这种方法能削弱异常数据的影响。在完全样本情形下, 我们获得了指数威布尔分布参数的最小二乘估计和加权最小二乘估计。最后给出数值模拟例子,结果显示模糊最小二乘估计是正确、有效的。