基于全经验信息累计比率的可加模型变量选择-概率论与数理统计专业论文.docxVIP

英文摘 英文摘要 基于全经验信息累计比率的可加模型变量选择 I II Variable selection for additive model via cumulative ratios of empirical strengths total Abstract This paper proposes a data-driven method to select significant variables in additive model via spline estimation. The additive structure of the regression model is imposed to overcome the “curse of dimensionality”, while the spline estimators provide a good approximation to the additive components of the model. The additive components are ordered according to their empirical strengths, and the significant variables are chosen at the first crossing of a predetermined threshold by the CUmulative Ratios of Empirical Strengths Total (CUREST) of the components. Consistency of the proposed method is established, while extensive Monte Carlo study demonstrates superior performance of the proposed method and its advantages over the BIC method of Huang and Yang (2004, JRSSB) in terms of speed and accuracy. Keywords: additive model; B spline; cumulative ratios of empirical strengths total (CUREST); lag selection; variable selection. Written by Miao Yang Supervised by Lijian Yang 目 录 第一章 号言 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 第二章 可加模型 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 第三章 样条估计 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 第四章 重要变量的选择 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 第五章 方法的实现 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 第六章 数据模拟 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 §6.1 自回归模型 . . . . . . .