响应变量缺失时纵向数据下变系数部分线性测量误差模型的经验似然推断  

Empirical likelihood inferences for longitudinal varying coefficient partially linear error-in-variables models with missing responses

作　　者：张明峰[1] 柳泽慧 周小双[3] 

机构地区：[1]德州学院科技处,山东德州253023 [2]华东师范大学金融与统计学院,上海200062 [3]德州学院数学科学学院,山东德州253023

出　　处：《山东大学学报（理学版）》2015年第11期127-134,共8页Journal of Shandong University(Natural Science)

基　　金：国家自然科学基金数学天元基金资助项目(11426057);山东省自然科学基金资助项目(ZR2014AL005;ZR2012AL05)

摘　　要：将经验似然方法应用于响应变量缺失时纵向数据下变系数部分线性测量模型中兴趣参数置信域,构造了关于参数分量纠衰的分块经验对数似然比函数,进而推导出参数分量纠衰的分块经验似然比统计量及其渐近分布。数据模拟结果表明所提出的经验似然方法在置信区间长度和覆盖率方面要优于正态逼近方法。Empirical likelihood inferences for the parameter component in varying coefficient partially linear errors-in- variables models with longitudinal data and missing responses were investigated. A corrected-attenuation block empirical likelihood procedure was used to estimate the unknown parameter vector, and a corrected-attehuation block empirical log-likelihood ratio statistic was suggested and its asymptotic distribution was obtained. Simulation results indicate that our proposed method performs better than the method based on normaJ approximations in terms of relatively higher coverage probabilities and smaller confidence regions.

关 键 词：变系数部分线性模型 经验似然 缺失数据 纵向数据 测量误差 

分 类 号：O212.7[理学—概率论与数理统计]