摘要
大量实证研究表明,半参数自回归模型较传统的线性回归而言,能更好的拟合实际数据。本文构造了一类半参数可加自回归模型,基于条件最小二乘方法及核估计方法给出了估计模型参数和未知函数的迭代算法,讨论了估计量的渐近性质。通过数值模拟验证了估计的效果。并将模型应用于黄金价格数据的实证分析之中。实证分析结果表明,我们对现有模型的改进是必要的。
A large number of empirical studies show that semiparametric autoregressive models can better fit real data than traditional linear regression models.In this paper,a class of semiparametric additive autoregressive models is constructed.Based on the conditional least squares and kernel estimation methods,an iterative algorithm for estimating the unknown parameters and nonparametric functions of the model is given.The asymptotic properties of the estimators are discussed.The effect of the estimation was verified by numerical simulations.Finally,the model is applied to the empirical analysis of gold price data.The empirical analysis shows that it is necessary to improve the existing model.
作者
杨凯
赵洪梅
刁亚静
李纯净
YANG Kai;ZHAO Hong-mei;DIAO Ya-jing;LI Chun-jing(School of Mathematics and Statistics,Changchun University of Technology,Changchun 130012,China)
出处
《数理统计与管理》
CSSCI
北大核心
2020年第1期154-161,共8页
Journal of Applied Statistics and Management
基金
国家自然科学基金项目(11901053,11571051)
吉林省教育厅“十三五”科学技术研究规划项目(2016316)
关键词
半参数可加自回归模型
核估计
黄金价格
semiparametric additive autoregressive models
kernel estimation
gold prices
