及时性自适应高维经济基本面建模与汇率预测分析

李欣珏

系统工程理论与实践 ›› 2020, Vol. 40 ›› Issue (6) : 1478-1494.

PDF(978 KB)
中国科学院数学与系统科学研究院期刊网
PDF(978 KB)
系统工程理论与实践 ›› 2020, Vol. 40 ›› Issue (6) : 1478-1494. DOI: 10.12011/1000-6788-2020-0466-17
论文

及时性自适应高维经济基本面建模与汇率预测分析

    李欣珏1,2
作者信息 +

The real time adaptive high dimensional economic basics modeling with application in exchange rate forecasting

    LI Xinjue1,2
Author information +
文章历史 +

摘要

在人民币国际化不断推进，人民币汇率双向波动加强的背景下，构建具有优良预测能力的汇率预测模型愈发重要.参数模型对汇率预测的能力不仅取决于模型设定是否正确，还取决于模型能够同时：一方面能否迅速探测模型参数的结构性变化以使用最佳信息估计模型参数，另一方面能否及时识别模型解释变量以使用最佳解释变量对汇率进行预测.本文构建了自适应变元算法.该算法不仅能实时检测模型参数的结构性变化，探测参数的最大化同质区间，同时还能对变量进行及时识别以选择最佳模型解释变量，提高模型的预测能力.在样本外向前3至24个月的汇率预测中，自适应变元算法能显著超越随机游走，马尔可夫机制转换模型，误差修正模型，实时最优窗算法，多元自适应可变窗算法与其他经济基本面模型包括：弹性货币模型，购买力平价模型，利率平价模型，泰勒规则模型，偏移泰勒规则模型.变量选择结果显示，自"811"汇改以后，经济基本面因素决定了人民币汇率走势.中国与其他发达经济体包括欧元区，英国与日本的经济基本面同样能够决定美元兑人民币汇率走向.另外，自"811"汇改之后，人民币汇率预期相比于"811"汇改之前更易受到外部冲击的影响，合理的人民币汇率预期监管依然需要依赖于实行有管理的浮动汇率制度，防止汇率风险.

Abstract

To develop an outstanding Renminbi exchange rate forecasting model based on the background of Renminbi internationalization and the increased two-way volatility becomes much more important. The forecasting ability of a parameter model depends not only on whether it is correctly specified, but also on one hand the efficiency of whether it can detect the structure changes and using the effective observations to estimate the parameters, and on the other hand on the ability of selecting the proper covariates that can be used in forecasting. In order to solve these required problems, this paper has developed the penalized adaptive method which can adaptively select the covariates and detect the structure changes. The developed model can outperform the local adaptive method and other economic fundamental methods in exchange rate predictions. In the USD against RMB exchange rate regime, we find out that the newly developed methods can manage of significantly increasing the forecasting accuracy compared with the second-best model. After the 811-exchange-rate-reform, the economic fundamentals have been significantly improved in determining the exchange rate expectation. Moreover, after the 811-exchange-rate-reform, the exchange rate of USD against RMB itself does not decide alone by the USD. It is also decided heavily by the other fundermental differences between China and the other developed countries such as UK, Euro Zone and Japan. The manageable floating exchange rate system is also crucial in preventing the exchange rate risk in China.

关键词

经济基本面 / 汇改 / 汇率预测 / 自适应变元算法

Key words

economic fundamentals / exchange rate reform / exchange rate forecasting / penalized adaptive method

引用本文

EndNote

Ris (Procite)

Bibtex

导出引用
李欣珏. 及时性自适应高维经济基本面建模与汇率预测分析. 系统工程理论与实践, 2020, 40(6): 1478-1494 https://doi.org/10.12011/1000-6788-2020-0466-17
LI Xinjue. The real time adaptive high dimensional economic basics modeling with application in exchange rate forecasting. Systems Engineering - Theory & Practice, 2020, 40(6): 1478-1494 https://doi.org/10.12011/1000-6788-2020-0466-17
中图分类号： F064.1   

参考文献

[1] Galimberti J K, Moura M L. Taylor rules and exchange rate predictability in emerging economies[J]. Journal of International Money and Finance, 2013, 32:1008-1031.
[2] Molodtsova T, Papell D H. Out-of-sample exchange rate predictability with Taylor rule models[J]. Journal of International Economics, 2009, 77(2):167-180.
[3] Engel C, Mark N C, West K D. Factor model forecasts of exchange rates[J]. Econometric Reviews, 2015, 34(1-2):32-55.
[4] Ince O, Molodtsova T, Papell D H. Taylor rule deviations and out-of-sample exchange rate predictability[J]. Journal of International Money and Finance, 2016, 69:22-44.
[5] 陈平, 李凯. 人民币汇率与宏观基本面:来自汇改后的证据[J]. 世界经济, 2010(9):28-45. Chen P, Li K. RMB exchange rate and macro fundamentals:Evidence from exchange rate reform[J]. The Journal of World Economy, 2010(9):28-45.
[6] 邓贵川, 李艳丽. 汇率基本面模型对人民币汇率的预测能力[J]. 数量经济技术经济研究, 2016(9):145-160.Deng G C, Li Y L. Forecasting ability of different fundamental exchange rate model on RMB[J]. The Journal of Quantitative & Technical Economics, 2016(9):145-160.
[7] Rossi B, Sekhposyan T. Understanding models' forecasting performance[J]. Journal of Econometrics, 2011, 164(1):158-172.
[8] Inoue A, Jin L, Rossi B. Rolling window selection for out-of-sample forecasting with time-varying parameters[J]. Journal of Econometrics, 2017, 196(1):55-67.
[9] 李欣珏, 牛霖琳. 汇率预测及其经济基本面:基于多元自适应可变窗算法的构建[J]. 统计研究, 2019, 36(9):43-55. Li X J, Niu L L. Exchange rate forecasting and its economic fundamentals:Based on multivariable adaptive rolling window algorithm modeling[J]. Statistical Research, 2019, 36(9):43-55.
[10] Fujikoshi Y, Sakurai T. Some properties of estimation criteria for dimensionality in principal component analysis[J]. American Journal of Mathematical and Management Sciences, 2016, 35(2):133-142.
[11] Bai Z, Fujikoshi Y, Hu J. Strong consistency of the AIC, BIC, Cp and Koo methods in high-dimensional linear regression[R]. 2018, arXiv:1810.12609v2.
[12] Zou H, Li R. One-step sparse estimates in nonconcave penalized likelihood models[J]. Annals of Statistics, 2008, 36(4):1509-1533.
[13] Bai J, Ng S. Forecasting economic time series using targeted predictors[J]. Journal of Econometrics, 2008, 146(2):304-317.
[14] 刘啟仁, 黄建忠. 人民币汇率、依市场定价与资源配置效率[J]. 经济研究, 2016(12):20-33.Liu Q R, Huang J Z. Renminbi exchange rate, pricing to market and misallocation[J]. Economic Research Journal, 2016(12):20-33.
[15] 陈创练, 姚叔洁, 郑挺国, 等. 利率市场化、汇率改制与国际资本流动的关系研究[J]. 经济研究, 2017(4):64-77.Chen C L, Yao S J, Zheng T G, et al. Interest rate liberalization, exchange rate reform, and international capital flow[J]. Economic Research Journal, 2017(4):64-77.
[16] 彭红枫, 谭小玉. 人民币国际化研究:程度测算与影响因素分析[J]. 经济研究, 2017(2):125-139.Peng H F, Tan X Y. RMB internationalization:Degree measurement and determinants analysis[J]. Economic Research Journal, 2017(2):125-139.
[17] Wang R, Morley B, Stamatogiannis M P. Forecasting the exchange rate using nonlinear Taylor rule based models[J]. International Journal of Forecasting, 2019, 35(2):429-442.
[18] Suvorikova A, Spokoiny V, Buzun N. Multiscale parametric approach for change point detection[C]//Information Technology and Systems, ITaS, 2015:979-996. http://itas2015.iitp.ru/en/search.html.
[19] Fan J, Li R. Variable selection via nonconcave penalized likelihood and its oracle properties[J]. Journal of the American Statistical Association, 2001, 96(456):1348-1360.
[20] Zhao P, Yu B. On model selection consistency of LASSO[J]. Journal of Machine Learning Research, 2006, 7(12):2541-2563.
[21] Kim Y, Choi H, Oh H S. Smoothly clipped absolute deviation in high dimensions[J]. Journal of the American Statistical Association, 2008, 103(484):1665-1673.
[22] Wang H, Leng C. Unified LASSO estimation by least squares approximation[J]. Journal of the American Statistical Association, 2007, 102(479):1039-1048.
[23] Chand S. On tuning parameter selection of LASSO-type method-A Monte Carlo study[C]//Proceedings of 9th International Bhurban Conference on Applied Sciences & Technology, 2012:120-129.
[24] Spokoiny V, Zhilova M. Bootstrap confidence sets under model misspecification[J]. The Annals of Statistics, 2015, 43(6):2653-2675.
[25] Li X, Zboňáková L, Wang W, et al. Combining penalization & adaption in high dimension with application in bond risk premia forecasting[C]//IRTG 1792 Discussion Papers, 2019-030. https://www.wiwi.hu-berlin.de/de/forschung/irtg/results/discussion-papers.
[26] Kwon S, Kim Y. Large sample properties of the SCAD-penalized maximum likelihood estimation on high dimensions[J]. Statistica Sinica, 2012, 22(2):629-653.
[27] Diebold F, Mariano R. Comparing predictive accuracy[J]. Journal of Business and Economic Statistics, 1995, 13:253-265.
[28] 杨荣海, 李亚波. 资本账户开放对人民币国际化"锚货币"地位的影响分析[J]. 经济研究, 2017(1):134-148.Yang R H, Li Y B. Capital account liberalization and the anchor currency status of RMB during its globalization process[J]. Economic Research Journal, 2017(1):134-148.
[29] 孙彦林, 陈守东, 刘洋. 基于股市和汇市成交量信息视角的股价波动预测[J]. 系统工程理论与实践, 2019, 39(4):935-945.Sun Y L, Chen S D, Liu Y. Forecast of stock price fluctuation based on the perspective of volume information in stock and foreign exchange market[J]. Systems Engineering-Theory & Practice, 2019, 39(4):935-945.
[30] 彭程, 李爽, 包莹, 等.外汇欧式期权在市场不完备下的对冲误差分析[J]. 系统工程理论与实践, 2019, 39(11):2739-2749.Peng C, Li S, Bao Y, et al. Hedging error analysis of foreign exchange European options under incomplete market[J]. Systems Engineering-Theory & Practice, 2019, 39(11):2739-2749.
[31] 郑振龙, 王磊. 汇率相关性预测的比较研究[J]. 金融研究, 2017(5):18-31.Zheng Z L, Wang L. A comparative study on the forecasting of the correlation between FX rates[J]. Journal of Financial Research, 2017(5):18-31.
[32] Fan J, Peng H. Nonconcave penalized likelihood with a diverging number of parameters[J]. Annals of Statistics, 2004, 32(3):928-961.

基金

国家自然科学基金（71871193）
PDF(978 KB)

484

Accesses

0

Citation

Detail
段落导航
相关文章

/

〈 〉