协变量随机缺失下线性模型的经验似然推断及其应用  

Empirical Likelihood for Linear Models with Covariate Data Missing at Random

作　　者：杨宜平[1] 

机构地区：[1]重庆工商大学数学与统计学院,重庆400067

出　　处：《数理统计与管理》2011年第4期655-663,共9页Journal of Applied Statistics and Management

基　　金：国家自然科学基金(10871013;10871217);北京市自然科学基金(1102008);高等学校博士学科点专项科研基金(20101103120016);重庆工商大学科研启动经费项目(20105609)

摘　　要：考虑协变量带有缺失的线性模型，提出了加权的经验似然方法和借补的经验似然方法，证明了所提出的经验对数似然比渐近于x^2分布，由此构造回归系数的置信域。模拟研究了所提出方法的有限样本性质，并进行了实例分析。Linear models with covariate data missing at random are considered, the weighted empirical likelihood and the imputed empirical likelihood are proposed. The proposed empirical log-likelihood ratios are proven to be asymptotically chi-squared, and the corresponding confidence regions for the regression coefficients are then constructed. The finite sample behavior of the proposed method is evaluated with simulation study, and a real example is analyzed.

关 键 词：线性模型 随机缺失 经验似然 X^2分布 

分 类 号：O212.7[理学—概率论与数理统计]