左截断右删失数据下尺度参数与协变量相关时广义指数分布的估计及应用  

Estimation and Application of Generalized Exponential Distribution of Scaling Parameter in Relation to Covariate under Left Truncated and Right Censored Data

作　　者：赵波 王纯杰 李群 佟知真 ZHAO Bo;WANG Chunjie;LI Qun;TONG Zhizhen(School of Mathematics and Statistics,Changchun University of Technology,Changchun 130012,China)

机构地区：[1]长春工业大学数学与统计学院,长春130012

出　　处：《吉林大学学报（理学版）》2018年第4期864-870,共7页Journal of Jilin University:Science Edition

基　　金：国家自然科学基金(批准号:11671054;11571051;11301037);吉林省教育厅"十三五"规划项目(批准号:2016317)

摘　　要：在左截断右删失数据类型下,当时间变量T服从广义指数分布时,针对尺度参数是否受协变量影响建立两种模型,并用极大似然估计法给出参数估计,用Newton-Raphson算法求解参数估计.将两种模型分别应用到变压器寿命数据集和Channing house数据集中,得到了其生存函数和风险函数.Under the left truncated and right censored data,when the time variable T obeyed the generalized exponential distribution,in view of whether the scaling parameters were affected by covariates,we established two kinds of models,and used the maximum likelihood estimation method to estimate parameters.The Newton-Raphson algorithm was used to solve the estimation of the parameters.The two models were applied to the transformer life data set and the Channing house data set,respectively,we obtained its survival function and hazard function.

关 键 词：左截断右删失数据 广义指数分布 极大似然估计 Newton-Raphson算法 尺度参数回归 

分 类 号：O212[理学—概率论与数理统计]