区间删失下广义幂威布尔回归模型的参数估计  

Parametric estimation of generalized-power-Weibull regression models with interval-censored data

作　　者：祝佳佳[1] 田厚坤[1] 解锋昌[1] 

机构地区：[1]南京农业大学理学院,南京210095

出　　处：《华东师范大学学报（自然科学版）》2011年第2期47-53,88,共8页Journal of East China Normal University(Natural Science)

基　　金：江苏省自然科学基金(BK2008284)

摘　　要：为研究区间删失的观测数据,结合广义幂威布尔分布和非线性回归模型提出了广义幂威布尔非线性回归模型,并基于迭代法给出了模型中参数的极大似然估计.最后就不同危险函数、样本量和删失比,通过蒙特卡洛模拟说明了参数估计方法的有效性.In order to study interval-censored observation data,a class of generalized-power -Weibull non-linear regression models combing the generalized-power-Weibull distribution and the non-linear regression model was proposed,and the maximum likelihood estimates of the model parameters were obtained based on iteration.Finally,some Monte Carlo simulation results were given to illustrate the effectiveness of the proposed method in terms of different hazard functions,sample sizes and censoring proportions.

关 键 词：区间删失数据 广义幂威布尔分布 非线性回归 极大似然估计 蒙特卡洛模拟 

分 类 号：O212[理学—概率论与数理统计]