均值方差联合模型SEE变量选择.pdf

Statistics and Application 统计学与应用, 2017, 6(1), 98-103 Published Online March 2017 in Hans. /journal/sa /10.12677/sa.2017.61011 SEE Variable Selection for Joint Mean and Variance Models Ting Yao, Fengting Lu, Ruiqin Tian, Qiaoqiao Lv Department of Statistics, Zhejiang Agricultural and Forestry University, Hangzhou Zhejiang th th th Received: Mar. 9 , 2017; accepted: Mar. 26 , 2017; published: Mar. 29 , 2017 Abstract The method based on modeling the variance is one of the most commonly used methods to deal with heteroscedasticity. In this paper, we propose a variable selection procedure based on the smooth threshold estimating equations for joint mean and variance models. The proposed varia- ble selection method can select variables and estimate coefficients simultaneously, and does not need to solve convex optimization problem so as to largely reduce computation quantity in prac- tice. Finally, we make some simulations to show that the proposed procedure works satisfactorily. Keywords Joint Mean and Variance Models, Heteroscedasticity, Estimating Equation, Variable Selection 均值方差联合模型的SEE变量选择 姚 婷，陆凤婷，田瑞琴，吕巧巧 浙江农林大学统计系，浙江 杭州 收稿日期：2017年3月9 日；录用日期：2017年3月26 日；发布日期：2017年3月29 日 摘 要 对方差建立回归模型分析是处理异方差问题中最常用的方法之一。本文基于均值方差联合模型，结合光 滑阈估计方程(Smooth Threshold Estimating Equation，简记SEE)方法研究该模型的变量选择方法。该 变量选择方法可以同时进行参数估计和变量选择，并且不需要解任何凸优化问题，因此实际应用中将大 大减少计算量。最后, 通过随机模拟实验验证了所提出方法的有效性与可行性。 文章引用: 姚婷, 陆凤婷, 田瑞琴, 吕巧巧. 均值方差联合模型的SEE 变量选择[J]. 统计学与应用, 2017, 6(1): 98-103. /10.12677/sa.2017.61011 姚婷 等 关键词 均值方差联合模型，异方差，估计方程，变量选择 Copyright © 2017 by authors and Hans Publishers Inc. This work is licensed under the Creative