响应变量缺失下线性EV模型中参数的经验似然推断  

Empirical Likelihood Inference for the Parameter of a Linear Error-variable Models with Missing Response

作　　者：魏成花 胡锡健[1] 

机构地区：[1]新疆大学数学与系统科学学院,新疆乌鲁木齐830046

出　　处：《数学的实践与认识》2014年第9期188-194,共7页Mathematics in Practice and Theory

基　　金：国家自然科学基金(41261087);新疆文科基地重大项目基金(0601920)

摘　　要：考虑了响应变量随机缺失情形下的线性EV模型,通过利用逆概率加权的方法构造未知参数的经验对数似然比统计量,证明了所构造的经验对数似然比统计量渐近于X^2分布。The missing response problem in the linear EV（error-variables） models is inves- tigated. Using the inverse probability-weighted method, the empirical log-likelihood ratio statistics for the unknown parameter in the model is constructed. It is proved that the proposed statistics are asymptotically chi-square under some suitable conditions, with this results, the confidence region for the parameter can be constructed.

关 键 词：线性EV模型 缺失数据 经验似然 X^2分布 

分 类 号：O212.1[理学—概率论与数理统计]