Benchmarks and the accuracy of GARCH model estimation
Benchmarks and the accuracy of GARCH model estimation
复制标题
DOI：
10.1016/s0169-2070(00)00070-4
复制
发表时间：
2001-01-01
影响因子：
7.9
通讯作者：
Persand, G
中科院分区：
文献类型：
--
作者：
Brooks, C;Burke, SP;Persand, G
本文回顾了九个软件包，特别是参考他们的GRESS模型估计精度时，对一个受人尊敬的基准判断。我们考虑了Gestival和EGestival估计和预测的数值一致性。我们的研究结果对已发表的研究和未来的软件开发有一定的影响。最后，我们认为，建立其他标准的非线性模型的基准是早就应该。(C)2001年国际预报员协会。出版社：Elsevier Science BN All rights reserved.
This paper reviews nine software packages with particular reference to their GARCH model estimation accuracy when judged against a respected benchmark. We consider the numerical consistency of GARCH and EGARCH estimation and forecasting. Our results have a number of implications for published research and future software development. Finally, we argue that the establishment of benchmarks for other standard non-linear models is long overdue. (C) 2001 International Institute of Forecasters. Published by Elsevier Science BN. All rights reserved.