汇率货币模型的非线性协整关系检验——基于深度GRU神经网络

doi:10.16381/j.cnki.issn1003-207x.2020.05.001

摘要/Abstract

摘要： 本文采用深度门控循环单元（GRU）神经网络探讨三种汇率货币模型（弹性价格、前瞻性和实际利率差模型）的非线性协整关系。GRU技术在深度学习中具有智能记忆、自主学习和强逼近能力等优点。为此，本文运用该技术对6组典型浮动汇率制国别数据进行了非线性Johansen协整检验。结果表明，汇率与宏观经济基本面之间存在非线性协整关系，从而说明了货币模型在非线性条件下的有效性，以及先进的深度学习工具在检验经济理论中的优势。

关键词: 汇率, 货币模型, 非线性协整, 深度GRU神经网络

Abstract: The monetary model of exchange rate has been the focus of academic that many scholars have conducted linear cointegration test on it, which the results are not satisfactory.In this paper, three versions of monetary models of exchange rate determinations (Flexible price, Forward-looking and Real Interest Differential Models) are tested for six selected countries with floating exchange rate regimes, by applying the nonlinear Johansen cointegration tests, facilitated by the Gated Recurrent Unit (GRU) neural network technique. The GRU technique has the advantages of intelligent memory, autonomous learning and strong approximation ability in deep learning. Based on country-by-country analysis, evidence of nonlinear cointegration between exchange rates and macroeconomic fundamentals is found. This suggests the validity of monetary models and the advantage of advanced deep learning tools in testing economic theory.
The concrete steps of the nonlinear cointegration test in this paper are: First, the long memory characteristics of the sequences are tested, because if there is a nonlinear cointegration relationship between the data sequences, it means that the sequence data must have the long memory characteristics. Secondly, the deep GRU neural network method is used to construct the nonlinear cointegration function, which has the transfer memory function that the ordinary neural network does not have, and has the advantage on the time series data mining. Finally, test whether the residuals of the constructed GRU model are short memory sequences (SMM). If the residuals are short memory sequences, the GRU can extract the non-linear characteristics between the sequences and prove the existence of nonlinear cointegration relationship between the sequences.
The results show that: (1) The original sequence after normalization has the feature of long memory, which is suitable for the discussion with the nonlinear cointegration theory. (2) The residual of the nonlinear cointegration model constructed by GRU neural network is short memory sequence, which found evidence of nonlinear cointegration between exchange rates and macroeconomic fundamentals.
In this paper, advanced deep GRU technology is introduced into nonlinear cointegration test, which can play a role in attracting valuable contributions to expand the tool box of cointegration empirical test.

Key words: exchange rate, monetary models, nonlinear cointegration, the deep GRU neural network

中图分类号:

陆晓琴, 冯玲, 丁剑平. 汇率货币模型的非线性协整关系检验——基于深度GRU神经网络[J]. 中国管理科学, 2020, 28(5): 1-13.

LU Xiao-qin, FENG Ling, DING Jian-ping. Testing the Nonlinear Cointegration Relation of Monetary Models of Exchange Rate Determination ——An Analysis Based on the Deep GRU Neural Network[J]. Chinese Journal of Management Science, 2020, 28(5): 1-13.

参考文献

[1] Frenkel J.A monetary approach to the exchange rate:Doctrinal aspects and empirical evidence[J].Scandinavian Journal of Economics, 1976,78(2):200-224.
[2] Mussa M. The exchange rate, the balance of payments, and monetary and fiscal policy under a regime of controlled floating[J].Scandinavian Journal of Economics,1976,78(2):229-248.
[3] Bilson J F. Rational expectations and the exchange rate[J]. Economics of Exchange Rates, 1978:75-96.
[4] MacDonald R, Taylor M P. The monetary model of the exchange rate:Long-run relationships, short-run dynamics and how to beat a random walk[J].Journal of International Money and Finance,1994, 13(3):276-290.
[5] Wong M. A monetary approach to the sterling-US dollar exchange rate[D].London:Middlesex University Business School, 2004.
[6] Cerra V, Saxena S C. The monetary model strikes back:evidence from the world[J].Journal of International Economics, 2010,81(2):184-196.
[7] 潘素昆,文婧. FDI对人民币实际汇率即期影响研究[J]. 中国管理科学,2012,20(S1):404-408.
[8] 余湄,卢雪. 汇改后外国直接投资对人民币实际汇率的影响研究[J]. 中国管理科学,2014,22(S1):247-252.
[9] Meese R A, Rogoff K.Empirical exchange rate models of the seventies:do they fit out-of sample?[J].Journal of International Economics,1983,(14):3-24.
[10] Meese R A, Rogoff K.The out of sample failure of empirical exchange rate models:sampling error or mis-specification?[M]//Jacob A. Frenkel. Exchange Rates and International Macroeconomics. Chicago:University of Chicago Press, 1983:67-112.
[11] Cheung Y W, Chinn M D, Garcia Pascual. Empirical exchange rate models of the nineties:are any fit to survive?[J]. Journal of International Money and Finance, 2005,24(7):1150-1175.
[12] Baillie R T, Selover D D.Cointegration and models of exchange rate determination[J].International Journal of Forecasting, 1987,3(1):43-51.
[13] Kearney C, Macdonald R.Rational expectations, bubbles and monetary models of the exchange rate:the australian/us dollar rate during the recent float[J]. Australian Economic Papers, 1990,29(54):1-20.
[14] 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,2010,33(9):28-45.
[15] Dinçer Afat. The failure of the monetary model of exchange rate determination[J].Applied Economics, 2015,47(43):4607-4629.
[16] 丁剑平,谌卫学. 汇率非线性因素在部分亚洲货币汇率中的特征——检验购买力平价论的新方法[J].财经研究,2010, 36(2):4-14.
[17] Grote C, Sibbertsen P. Testing for cointegration in a double-LSTR framework[M]//Jan Beran, Yuanhua Feng,Hartmut Hebbel. Empirical Economic and Financial Research. Switzerland:Springer International Publishing, 2015:437-450.
[18] Imad A, Ming Ma. Linear and nonlinear attractors in purchasing power parity[J].Economia Internazionale, 2018,71(2):149-172.
[19] Meese R A,Rose A K.An empirical assessment of non-linearities in models of exchange rate determination[J].International Finance Discussion Papers, 1991,58(58):603-619.
[20] Granger C W. Essays in Econometrics[M].Cambridge:Cambridge University Press, 1995.
[21] 张喜彬,孙青华,张世英.非线性协整关系及其检验方法研究[J].系统工程学报, 1999, 14(1):59-70.
[22] 孙青华,张喜彬,张世英.非线性协整关系的存在性研究[J].管理科学学报, 2000, 3(3):65-88.
[23] 樊智,张世英.非线性协整建模研究及沪深股市实证分析[J].管理科学学报, 2005, 8(1):73-77.
[24] 史代敏.沪深股市股指波动的协整性研究[J].数量经济技术经济研究, 2002, (9):103-105.
[25] 苏治,卢曼,李德轩.深度学习的金融实证应用:动态、贡献与展望[J].金融研究, 2017, (5):111-126.
[26] 舒晓惠.非线性协整时间序列的非参数方法及其应用研究[D].广州:暨南大学, 2010.
[27] Xiong R, Nichols E P, Shen Y. Deep learning stock volatility with google domestic trends[R].Working Paper, arXiv e-prints, 2015.
[28] 曹赢.量化宽松货币政策研究[D].浙江:浙江大学, 2017.
[29] Cho K, Merrienboer B V, Gulcehre C, et al. Learning phrase representations using rnn encoder-decoder for statistical machine translation[C]//Proceedings of Empirical Methods in Natural Language, Doha, Qatar,October 25-29, Association for Computational Linguistics, 2014:1724-1734.
[30] 牛哲文等.基于深度门控循环单元神经网络的短期风功率预测模型[J].电力自动化设备, 2018, 38(5):36-42.
[31] 李雪莲.基于门循环单元神经网络的中文分词法[J].厦门大学学报(自然科学版), 2017, 56(2):237-243.
[32] 黄兆玮等. 基于GRU和注意力机制的远程监督关系抽取[J].计算机应用研究,2019, 36(10):2930-2933.
[33] Dey R, Salemt F M. Gate-variants of Gated Recurrent Unit (GRU) neural networks[C]//Proceedings of IEEE International Midwest Symposium on Circuits and Systems, Boston,MA, August 6-9, IEEE, 2017:1597-1600.
[34] Li L, Wan J, Zheng J, et al. Biomedical event extraction based on GRU integrating attention mechanism[J]. Bmc Bioinformatics, 2018, 19(S9):177-184.
[35] Dornbuschn R. Expectations and exchange rate dynamics[J].Journal of Political Economy,1976, 84(6):1161-1176.
[36] Frankel J A. On the mark:a theory of floating exchange rates based on real interest differentials[J].American Economic Review, 1979,69(4):610-622.
[37] 许启发,蒋翠侠,张世英.基于小波多分辨分析的协整建模理论与方法的扩展[J].统计研究, 2007, 24(8):92-96.
[38] 黄超,黄丽丽.基于双正交小波支持向量机的变结构非线性协整研究[J].管理工程学报, 2014, 28(4):158-206.
[39] Hurst H E.Long term storage capacity of reservoirs[J].Transactions of the American Society of Civil Engineers,1951, 116(1):770-799.
[40] LoAdrew W. Long-term memory in stock market prices[J].Econometrica, 1991, 59(5):1279-1313.
[41] Lloyd E H,Hurst H E, Black R P,et al.Long-term storage:an experimental study[J].Journal of the Royal Statistical Society, 1966,129(4):591.
[42] 彼得斯.资本市场的混沌与秩序[M].北京:经济科学出版社,1999.
[43] 钟正生,高伟.我国消费者价格指数长记忆性研究[J]. 财贸经济, 2009, (7):127-133.
[44] 谢赤,岳汉奇.汇率收益率及其收益波动率存在长记忆性吗?——基于人民币汇率和欧元汇率的经验分析[J].经济评论, 2012, (4):135-144.
[45] Baillie R T, Chung C F, Tieslau M A. Analysing inflation by the fractionally integrated ARFIMA-GARCH model[J].Journal of Applied Econometrics, 1996,11(1):23-40.
[46] 程细玉,张世英.向量分整序列的协整研究[J].系统工程学报, 2000, 15(3):253-266.
[47] Georgoutsos D A, Kouretas G P. The relevance of the monetary model for the Euro/USD exchange rate determination:a long run perspective[J]. Open Economies Review, 2017, 28(5):1-22.