多个Kotz分布总体参数基于序约束下的极大似然估计  

Maximum Likelihood Estimation of the Parameters of the Multiple Kotz-type Distribution Based on Order Restrictions

作　　者：王寿贤 李树有[1] 宓颖[1] 

机构地区：[1]辽宁工业大学理学院,辽宁锦州121001

出　　处：《辽宁工业大学学报（自然科学版）》2016年第1期53-59,共7页Journal of Liaoning University of Technology(Natural Science Edition)

基　　金：国家自然科学基金资助项目(11271064)

摘　　要：研究了多个kotz分布总体的参数基于序约束下的极大似然估计问题,并给出了多个kotz分布总体未知参数的极大似然估计的算法,根据PAVA算法又给出了k个kotz分布总体的参数在简单半序,伞形半序,简单树半序和简单环半序约束下的极大似然估计。还讨论了多个kotz分布总体参数基于截尾样本的极大似然估计的计算方法。Maximum likelihood estimation of parameters of multiple Kotz-type distribution based on order restrictions was studied. The method about the maximum likelihood estimation of the unknown parameters of the multiple Kotz-type distribution was given. Based on the PAVA algorithm,maximum likelihood estimation of parameters of k Kotz-type distribution based on order restrictions was given too, such as, simple order, umbrella semi-order, simple tree order and simple ring order. Maximum likelihood estimation of parameters of multiple Kotz-type distribution based on censored samples was discussed.

关 键 词：kotz分布 极大似然估计 半序约束 

分 类 号：O212[理学—概率论与数理统计]