统计研究 ›› 2007, Vol. 24 ›› Issue (11): 74-79.

• 论文 • 上一篇    下一篇

具有GARCH(1,1)-正态误差项的非对称单位根检验研究

刘汉中   

  1. 华中科技大学
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-11-15 发布日期:2007-11-15

Research on Asymmetric Unit-root Test on a GARCH (1,1) with Normal Errors

Liu Hanzhong   

  • Received:1900-01-01 Revised:1900-01-01 Online:2007-11-15 Published:2007-11-15

摘要: 摘  要:理论研究表明许多经济变量呈现出非对称的门限自回归(TAR)或动态门限自回归(M-TAR)数据生成机制,因而非对称单位根检验就成为该领域的主要研究方向之一。本文对非对称单位根检验Enders-Granger方法在GARCH(1,1)-正态误差项下的检验水平与检验势作了系统的仿真研究。研究表明:GARCH(1,1)-正态误差项的TAR或M-TAR模型会对该方法的检验水平和检验势产生重要影响。

Abstract: Abstract:Theory studies show that many important economic variables have data generation process of asymmetric threshold autoregressive models or momentum threshold autoregressive models, as a result, the focus of this fields has changed to the asymmetric unit root test. This paper has simulated the test size and test power of Enders-Granger method under GARCH( 1,1 ) with normal errors, and the results of Monte-Carlo simulation show that the GARCH( 1,1 ) with normal errors plays an important role in the test size and test rower of Enders-Granger method in a TAR model or M-TAR model.


 

Key words: Key words:TAR and M-TAR, Enders-Granger method, Monte-Carlo simulation, Test size and test power