基于Logistic总体Ⅱ型截尾样本分布参数的近似极大似然估计

Approximate Maximum Likelihood Estimation Based on Logistic Distribution Parameters of Type Ⅱ Censored Samples

为了研究Logistic总体的拟合优度检验问题等,讨论了基于Logistic总体Ⅱ型截尾样本分布参数的近似极大似然估计,得到如下结果:在样本大小足够大,样本双侧截尾比分别趋近于定值条件下,分布参数的近似极大似然估计存在、惟一、有界、且相合于真实参数;特别地,当样本双侧截尾比趋于同一定值时,估计量具有渐近正态性.

For the purpose of studying the goodness-of-fit testing of Logistic distribution, the authors discussed the titular problems. The results show that if the example is big enough and the type Ⅱ censored ratio is constant respectively, the approximate maximum likelihood estimation of distribution parameter still exists uniquely, has limit and is consistent to the real parameter; Particularly, if the cansored ratios tend to be a constant, the maximum likelihood estimation has the asymptotic normality.