黄金作为一种特殊的贵金属，不仅其本身具有货币和商品的双重功能，而且对经济领域有着重要影响，因此预测黄金价格趋势对社会经济发展具有重要意义。文中提出了一种新的预测方法：首先采用HP滤波将时间序列分解为趋势要素序列和周期波动序列；然后针对不同序列的性质，对趋势要素序列采用自回归模型（ AR）拟合预测，对周期波动序列采用ARMA-GARCH族模型拟合预测；最后将两个预测序列相加与原序列比较；预测结果在模型精度和范围上均令人满意。
Gold as a special kind of precious metal ,not only has the dual function of money and goods ,but also has important influence on economy ,therefore,prediction of gold price trends for investors and the development of so-cial economy are significant .This paper proposes a new forecasting model that first of all decomposes time sequences into trend factor sequences and periodic fluctuation sequences by HP filter .And for different time sequences , fitting prediction of trend factor sequence is made using autoregressive model (AR) model,while fitting prediction of periodic fluctuation sequences is made using ARMA -GARCH family model .Finally those two forecast sequences are added to-gether before compared to the original sequence ,proving to be acceptable on model precision and forecast range .
参考文献
| [1] | 张莹,胥莉,陈宏民.石油与黄金产业价格联动关系研究[J].财经问题研究,2007(07):35-39. |
| [2] | 付丹,梅雪,张晖.黄金价格与通货膨胀相关性的实证分析[J].黄金,2009(01):4-7. |
| [3] | Nicholas Apergis .Can gold prices the Australian dol ar movements[J].International Review of Economics and Finace,2013,30(04):1-8. |
| [4] | 彭潇熟,张德生,王若星,陈聪.国际黄金价格具有外生变量的GARCH预测模型[J].黄金,2011(01):10-14. |
| [5] | 潘贵豪,胡乃联,刘焕中,李国清.基于ARMA-GARCH模型的黄金价格实证分析[J].黄金,2010(01):5-8. |
| [6] | 张延利.新马尔科夫模型的黄金价格短期预测[J].黄金,2012(09):6-8. |
| [7] | 张均东,刘澄,孙彬.基于人工神经网络算法的黄金价格预测问题研究[J].经济问题,2010(01):110-114. |
| [8] | 曾黎,李春.融合线性、非线性模型的黄金价格预测模型研究[J].黄金,2013(03):7-10. |
| [9] | 魏宇,黄登仕,王建琼,朱宏泉,余江,赖晓东.我国黄金现货市场的动态VaR预测模型研究[J].管理评论,2010(08):30-38. |
| [10] | Shahriar Shafiee;Erkan Topal .An overview of global gold market and gold price forecasting[J].Resources policy,2010(3):178-189. |
| [11] | Ismail Z;Yahya A;Shabri A .Forecasting Gold Prices Using Multi-ple Linear Regression Method[J].American Journal of Applied Sciences,2009,33(06):1509-1514. |
| [12] | 郑秀田.基于GARCH-M模型的黄金市场风险与收益关系研究[J].黄金,2008(05):4-7. |
- 下载量()
- 访问量()
- 您的评分：
-
10%
-
20%
-
30%
-
40%
-
50%