考虑在函数型解释变量部分观测的情况下,用函数线性模型刻画与标量响应变量的关系.基于函数型主成分分析(Functional Principal Component Analysis,简称FPCA)实现了对缺失部分样本的重构,并通过实证分析,对一组北京市2010-2014年间统...考虑在函数型解释变量部分观测的情况下,用函数线性模型刻画与标量响应变量的关系.基于函数型主成分分析(Functional Principal Component Analysis,简称FPCA)实现了对缺失部分样本的重构,并通过实证分析,对一组北京市2010-2014年间统计的包括部分观测PM2.5数值的气象数据,分析了PM2.5作为部分观测函数型解释变量对标量响应变量平均气温的影响,结果表明了该方法具有处理缺失函数数据的现实意义.展开更多
In this paper, three smoothed empirical log-likelihood ratio functions for the parameters of nonlinear models with missing response are suggested. Under some regular conditions, the corresponding Wilks phenomena are o...In this paper, three smoothed empirical log-likelihood ratio functions for the parameters of nonlinear models with missing response are suggested. Under some regular conditions, the corresponding Wilks phenomena are obtained and the confidence regions for the parameter can be constructed easily.展开更多
Empirical likelihood （EL） ratio statistic on θ=g（x） is constructed based on the inverse probability weighted imputation approach in a nonparametric regression model Y = g（x） ＋ε （x ∈ [0, 1]p） with fixed des...Empirical likelihood （EL） ratio statistic on θ=g（x） is constructed based on the inverse probability weighted imputation approach in a nonparametric regression model Y = g（x） ＋ε （x ∈ [0, 1]p） with fixed designs and missing responses, which asymptotically has X1^2 distribution. This result is used to obtain a EL based confidence interval on θ.展开更多
文摘考虑在函数型解释变量部分观测的情况下,用函数线性模型刻画与标量响应变量的关系.基于函数型主成分分析(Functional Principal Component Analysis,简称FPCA)实现了对缺失部分样本的重构,并通过实证分析,对一组北京市2010-2014年间统计的包括部分观测PM2.5数值的气象数据,分析了PM2.5作为部分观测函数型解释变量对标量响应变量平均气温的影响,结果表明了该方法具有处理缺失函数数据的现实意义.
文摘In this paper, three smoothed empirical log-likelihood ratio functions for the parameters of nonlinear models with missing response are suggested. Under some regular conditions, the corresponding Wilks phenomena are obtained and the confidence regions for the parameter can be constructed easily.
基金supported by the National Natural Science Foundation of China(11271081)2013 Young Teachers Scientific Research Project of University of International Business and Economics(12QD12)
基金Supported by the National Natural Science Foundation of China (No.10971038)the Natural Science Foundation of Guangxi (No.2010GXNSFA013117)
文摘Empirical likelihood （EL） ratio statistic on θ=g（x） is constructed based on the inverse probability weighted imputation approach in a nonparametric regression model Y = g（x） ＋ε （x ∈ [0, 1]p） with fixed designs and missing responses, which asymptotically has X1^2 distribution. This result is used to obtain a EL based confidence interval on θ.
