基于WAVELET-GARCH组合方法的中国保险深度分析  

WAVELET-GARCH Method in the Application of China Insurance Penetration

作　　者：谷政[1] 张维[1] 

机构地区：[1]南京审计学院金融学院,江苏南京211815

出　　处：《江西科学》2013年第3期403-408,共6页Jiangxi Science

基　　金：江苏省教育厅高校哲学社会科学基金项目(2012SJB790035);南京审计学院人才引进项目;江苏高校优势学科"审计科学与技术"

摘　　要：提出了非平稳时间序列的WAVELET-GARCH组合分析方法,应用于中国保险深度的研究。介绍小波以及GARCH方法的数学原理,阐述此组合方法的一般步骤,即利用小波函数分解原时间序列,成为趋势项和周期项;对趋势项进行平稳性检验;用GARCH模型拟合趋势项,并应用于预测。通过中国保险深度的变化情况研究,实证结果表明该方法比直接二次多项式拟合预测的平均相对误差小2.15%,反映WAVELET-GARCH组合方法的有效性。In this article,WAVELET-GARCH method is established in the non-stationary time series and applied in the insurance penetration.The principle of WAVELET-GARCH method and the general steps of the WAVELET-GARCH method are introduced.That is,using the wavelet method to decompose the time series to the tendency part and general part,testing the station of the tendency part,GARCH method fitting the stationary tendency part.As an application,we use WAVELET-GARCH method to discuss the insurance penetration in China.The fact that the mean relative error is 2.15% less than the one by directly polynomial fitting up to two degree shows that WAVELET-GARCH method is more effective.

关 键 词：小波 趋势项 广义自回归条件异方差 预测 

分 类 号：O241[理学—计算数学] F842[理学—数学]