Please wait a minute...
高校应用数学学报  2019, Vol. 34 Issue (2): 127-    
    
固定效应部分线性单指数面板模型的快速有效估计及应用
丁飞鹏, 陈建宝
1. 江西师范大学数学与信息科学学院, 江西南昌330022;
2. 福建师范大学数学与信息学院, 福建福州350117;
3. 福建省公共服务大数据挖掘与应用工程技术工程中心, 福建福州350117
Fast efficient estimation and application of partially linear single index model with fixed effects
DING Fei-peng, CHEN Jian-bao
1. School of Mathematics and Information Science, Jiangxi Normal University, Nanchang 330022,China;
2. College of Mathematics and Informatics, Fujian Normal University, Fuzhou 350117, China;
3. Fujian Provincial Engineering Technology Research Center for Public Service, Fuzhou 350117,China
 全文: PDF(481 KB)  
摘要: 将最小二乘支持向量机(LSSVM)和二次推断函数法(QIF)相结合, 构造了
个体内具有相关结构的固定效应部分线性单指数面板模型的新估计方法; 在一定
的正则条件下, 证明了参数估计量的渐近正态性, 导出了非参数估计量的收敛速度;
Monte Carlo模拟了所述方法在各种相关结构下的有限样本表现, 并与惩罚二次推断
函数(PQIF)法进行了比较; 将估计技术应用于分析我国人口结构与居民消费率的关
系. 研究发现, 该方法改善了估计量的有效性, 应用效果良好, 程序运行速度快, 适合经
济变量间的线性和非线性关系研究以及大数据分析.
关键词: 固定效应部分线性单指数面板模型 最小二乘支持向量机 二次推导函数法渐近性 Monte Carlo模拟    
Abstract: By combination of least square vector machine (LSSVM) with quadratic inference func-
tions (QIF), this paper construct a new estimation method for partially linear single index panel model
with fixed effects when responses from the same cluster are correlated. Under some regular condition,
asymptotic normality of parametric estimators and convergence rate of non-parametric estimator are
derived. The ˉnite sample performances of the proposed method are investigated by Monte Carlo simu-
lation under di?erent correlation structures, and compared with penalized quadratic inference functions
method (PQIF). The proposed estimation techniques are applied to analyse the relationship between
population structure and residents’consumption rate. Our research results show that the e±ciency
of estimators are improved by the proposed method, application e?ects are good, program operation
has high speed, it is particularly suitable for analysis of linear, nonlinear relationship among economic
variables and big data.
Key words: partially linear single index panel model with fixed effects    least square support vector machine    quadratic inference function    asymptotic    Monte Carlo simulation
出版日期: 2019-07-04
CLC:  O212.1  
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
丁飞鹏
陈建宝

引用本文:

丁飞鹏, 陈建宝. 固定效应部分线性单指数面板模型的快速有效估计及应用[J]. 高校应用数学学报, 2019, 34(2): 127-.

DING Fei-peng, CHEN Jian-bao. Fast efficient estimation and application of partially linear single index model with fixed effects. Applied Mathematics A Journal of Chinese Universities, 2019, 34(2): 127-.

链接本文:

http://www.zjujournals.com/amjcua/CN/        http://www.zjujournals.com/amjcua/CN/Y2019/V34/I2/127

[1] 李坤明, 陈建宝. 非参数空间滞后模型的广义矩估计[J]. 高校应用数学学报, 2018, 33(2): 140-156.
[2] 刘维奇, 梁珊珊. 一类新的位置不变极值指数估计[J]. 高校应用数学学报, 2018, 33(2): 179-190.
[3] 白永昕, 田茂再. Poisson分布下基于鞍点逼近的慢性病风险差的置信区间构造[J]. 高校应用数学学报, 2017, 32(3): 253-266.
[4] 韩祥临, 莫嘉琪. 非线性超抛物型方程广义渐近解的研究[J]. 高校应用数学学报, 2017, 32(2): 156-164.
[5] 白永昕, 田茂再. 慢性病发病率置信区间的构造[J]. 高校应用数学学报, 2016, 31(2): 136-142.
[6] 李云霞. 长程相依过程精确渐近性的一般规律[J]. 高校应用数学学报, 2015, 30(2): 150-156.