带有GARCH误差的单位根过程的估计  

Estimation of the unit root processes with GARCH errors and a drift

作　　者：袁裕泽[1] 

机构地区：[1]闽江学院数学系,福建福州350108

出　　处：《浙江大学学报（理学版）》2014年第1期23-25,共3页Journal of Zhejiang University（Science Edition）

基　　金：福建省自然科学基金资助项目(2013J05012);教育部人文社会科学研究资助项目(10YJC90011);福建省教育厅A类项目(JA13261)

摘　　要：单位根过程在时间序列理论中占有重要地位.单位根过程能较好地刻画经济数据中经常呈现的非平稳状态,因此其在经济理论与实证中都有广泛的应用.在更新项只有二阶矩存在的条件下,讨论了带有GARCH(p,q)误差项与趋势项的单位根过程的最小二乘估计.并推导了基于最小二乘估计的Dickey-Fuller检验统计量的渐近分布.该结果在单位根检验中具有重要作用.Unit root processes are very important in time series theory. Unit root models are suitable for describing the nonstationary properties in many economics data. So they are widely applied in both economics theory and empir ical analysis. In this paper, least square estimation for nearly unit root processes with GARCH errors and a drift are discussed only under finite variance o{ innovations. And the asymptotic distributions of Dickey-Fuller tests are de- rived. This result is crucial in unit root test.

关 键 词：GARCH 单位根过程 Dickey—Fuller检验 

分 类 号：O211.1[理学—概率论与数理统计]