| GARCH(1,1)模型及其在汇率条件波动预测中的应用 |
| |
| 引用本文： | 苏岩,杨振海.GARCH(1,1)模型及其在汇率条件波动预测中的应用[J].数理统计与管理,2007,26(4):615-620. |
| |
| 作者姓名： | 苏岩 杨振海 |
| |
| 作者单位： | 北京工业大学应用数理学院,北京100023 |
| |
| 摘 要： | 检验人民币/日元汇率与波动的时间序列特征,证实存在简单单位根过程及条件异方差性。计算表明,其汇率变化率的ARMA及ARMA/GARCH组合模型的建模不成立,GARCH、EGARCH、IGARCH模型的建模效果接近,且GARCH(1,1)拟合效果最好。GARCH(1,1)模型的跨度为一年的样本外条件异方差预测,显示出该年末汇率的震荡,与实际情况一致。GARCH(1,1)是汇率数据建娱的首选模型。
|
| 关 键 词： | 汇率 波动 GARCH(1 1) 模型 |
| 文章编号： | 1002-1566（2007）04-0615-06 |
| 修稿时间： | 2006-05-19 |
GARCH(1,1) Model and Its Application in Forecasting Conditional Volatility of Exchange Rate |
| |
| SU Yan,YANG Zhen-hai.GARCH(1,1) Model and Its Application in Forecasting Conditional Volatility of Exchange Rate[J].Application of Statistics and Management,2007,26(4):615-620. |
| |
| Authors: | SU Yan YANG Zhen-hai |
| |
| Institution: | College of Applied Science, Beijing University of Technology, Beijing 100022 |
| |
| Abstract: | We examine time series features of RMB/Japanese yen exchange rates and volatility,results show the daily exchange rates have unit root and time-varying variances.We find that ARMA and ARMA/GARCH combinative model can not describe the returns of the exchange rates,GARCH,EGARCH,IGARCH have similar fitting effects and overall the GARCH(1,1) performs better than IGARCH(1,1) and EGARCH(1,1).Out-of-sample volatility prediction performance of one year confirms the actual higher volatility in the end of the year.The GARCH(1,1) model is recommended as the first selecting model for volatility analyses of exchange rate data. |
| |
| Keywords: | GARCH(1 1) |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
