摘 要:
本文介绍了长记忆模型及其检验方法,根据Bayes原理,提出了记忆参数的一种新的估计方法。在运用Teverovsky/Taqqu(1997)年提出的一种基于样本方差的直观方法的初步检验基础上,运用新的检验方法,以美元对人民币汇率为研究对象,说明了我国汇率波动的长记忆性。然后,将经典的GPH-估计与新方法所得出的Bayes-估计相比较,可以看出这种新的估计方法较之经典的GPH-估计要稳定。[著者文摘]
文章出处:
《应用数学》-2006年19卷3期 -479-483页
文献标识码:
A
文章编号:
1001-9847(2006)03-0479-05
Bayesian Estimation of and it's Application Long Memory Models to Exchange Rates
XU Li-xia , LIU Ci-hua, NIE Gao-qin (Department of Mathematics, Huazhong University of Science and Technology, Wuhan 430074,China)
Abstract:
We introduce long memory model and it's test methods. By means of Bayesian principle, we propose a new method for the estimate of the memory parameter. Based on a rather heuristic method proposed by Teverovsky/Taqqu (1997), we illustrate the existing of long memory in the volatility of daily US Dollar/China R. M. B. exchange rate series by using the new approach and comparison of GPH-estimator and the Bayes-estimator is shown by empirical study.[著者文摘]
Key words:
Long memory model ; ARFIMA; Spectral density
基金资助:
Supported by National Science Foundation of China (10301011)

学术















cqvip.com