数学物理学报(英文版) ›› 2009, Vol. 29 ›› Issue (2): 327-340.doi: 10.1016/S0252-9602(09)60033-3

• 论文 • 上一篇    下一篇

TESTING THE ADEQUACY OF GARCH-TYPE MODELS IN TIME SERIES

 吴鑑洪, 朱力行   

  1. College of Statistics and Mathematics, Zhejiang Gongshang University, Hangzhou 310018, China
  • 收稿日期:2006-08-30 修回日期:2007-09-07 出版日期:2009-03-20 发布日期:2009-03-20
  • 基金资助:

    This work was partially supported by a grant from the Research Grants Council of Hong Kong. Jianhong Wu was also supported by a grant from Humanities & Social Sciences in Chinese University (07JJD790154) and the Youth Talent Foundation of Zhejiang GongShang University (Q09-12)

TESTING THE ADEQUACY OF GARCH-TYPE MODELS IN TIME SERIES

Wu Jianhong, Zhu Lixing   

  1. College of Statistics and Mathematics, Zhejiang Gongshang University, Hangzhou 310018, China
  • Received:2006-08-30 Revised:2007-09-07 Online:2009-03-20 Published:2009-03-20
  • Supported by:

    This work was partially supported by a grant from the Research Grants Council of Hong Kong. Jianhong Wu was also supported by a grant from Humanities & Social Sciences in Chinese University (07JJD790154) and the Youth Talent Foundation of Zhejiang GongShang University (Q09-12)

摘要:

In this article a new approach for checking the adequacy of GARCH-type models in time series was proposed. The resulted tests involve weight functions, which provide them with the flexibility in choosing scores to enhance power performance. The choice of weight functions and the power properties of the tests are studied. For a large
number of alternatives, asymptotically distribution-free maximin test is constructed. The tests are asymptotically chi-squared under the null hypothesis and easy to implement. Simulation results indicate that the tests perform well.

关键词: GARCH-type models, maximin test, model diagnostic checking, score type test

Abstract:

In this article a new approach for checking the adequacy of GARCH-type models in time series was proposed. The resulted tests involve weight functions, which provide them with the flexibility in choosing scores to enhance power performance. The choice of weight functions and the power properties of the tests are studied. For a large
number of alternatives, asymptotically distribution-free maximin test is constructed. The tests are asymptotically chi-squared under the null hypothesis and easy to implement. Simulation results indicate that the tests perform well.

Key words: GARCH-type models, maximin test, model diagnostic checking, score type test

中图分类号: 

  • 62F05