混频非对称金融景气指数编制及应用研究——基于MF-MS-DFM模型的经验分析

›› 2019, Vol. 31 ›› Issue (8): 71-83.

混频非对称金融景气指数编制及应用研究——基于MF-MS-DFM模型的经验分析

周德才¹, 朱志亮¹, 纪应心^1,2, 余永垒^1,3

1. 南昌大学经济管理学院, 南昌 330031;
2. 南开大学经济学院数量经济研究所, 天津 300071;
3. 南开大学金融学院, 天津 300071

收稿日期:2017-01-06 出版日期:2019-08-28 发布日期:2019-09-11
通讯作者: 周德才(通讯作者),南昌大学经济管理学院副教授,硕士生导师,博士
作者简介:朱志亮,南昌大学经济管理学院硕士研究生;纪应心,南开大学经济学院数量经济研究所硕士研究生;余永垒,南开大学金融学院硕士研究生。
基金资助:
全国统计科学研究项目 (2018LZ09)；国家社会科学基金年度项目（17BTJ011）；江西省自然科学基金面上项目 (20171BAA208015)。

Construction and Application of Chinese Mixed Frequency Asymmetric Financial Prosperity Index——Based on an Empirical Analysis of MF-MS-DFM Model

Zhou Decai¹, Zhu Zhiliang¹, Ji Yingxin^1,2, Yu Yonglei^1,3

1. School of Economics and Management, Nanchang University, Nanchang 330031;
2. Institute of Quantitative Economics, School of Economics, Nankai University, Tianjin 300071;
3. School of Finance, Nankai University, Tianjin 300071

Received:2017-01-06 Online:2019-08-28 Published:2019-09-11

摘要/Abstract

摘要：

为充分利用混频数据信息，本文构建能够综合利用日月混频数据的混频马尔科夫机制转移动态因子模型(MF-MS-DFM)，对4个日度和3个月度金融数据组成的混频数据进行实证建模与估计，编制我国混频非对称金融景气指数(MFMS-FPI)，将其与宏观经济变量进行比较分析和相关性分析。结果表明：MFMS-FPI具有很好的实时性和有效性，并能有效刻画我国金融景气阶段变化和考虑时滞的货币政策周期变化，是宏观经济的先行和预测指标。建议政府机构编制MFMS-FPI，对我国金融景气阶段变化进行实时监测。

关键词: 金融景气指数, 混频数据, MF-MS-DFM模型, GDP, CPI

Abstract:

To make full use of the information of mixed frequency data, this paper constructsa Mixed Frequency Markov Switching Dynamics Factors Model (MF-MS-DFM) that can comprehensively use daily and monthly data and chooses mixed frequency data of four daily and six monthly financial variables to construct an empirical model for estimation. Then we work out China's Mixed Frequency Asymmetric Financial Prosperity Index (MFMS-FPI) and make a comparative analysis and correlation analysis between MFMS-FPI and macroeconomic variables. The studies imply that MFMS-FPI effectively identifies the changes of China's real time financial cycle and the monetary policy cycle with time lag, and MFMS-FPI is the leading and predictive index of macroeconomic variables. Therefore, we advise the relevant government organizations to construct MFMS-FPI to monitor the changes of China's financial cycle on a real time basis.

Key words: financial prosperity index, mixed frequency data, MF-MS-DFM model, CPI, GDP

周德才, 朱志亮, 纪应心, 余永垒. 混频非对称金融景气指数编制及应用研究——基于MF-MS-DFM模型的经验分析[J]. , 2019, 31(8): 71-83.

Zhou Decai, Zhu Zhiliang, Ji Yingxin, Yu Yonglei. Construction and Application of Chinese Mixed Frequency Asymmetric Financial Prosperity Index——Based on an Empirical Analysis of MF-MS-DFM Model[J]. , 2019, 31(8): 71-83.

参考文献

[1] 张一,吴宝秀,李喆.新兴市场国家间的金融危机传染效应研究[J].管理评论, 2016,28(5):23-34
[2] Persons W. M. An Index of General Business Conditions, 1875-1913[J]. Review of Economic Statistics, 1927,9(1):20-29
[3] Burns A. F., Mitchell W. C. Measuring Business Cycles[M]. New York:NBER, 1946
[4] Santiago G., Carlos M. J. Generalized Diffusion Indexes of Mexican State and Sectorial Economic Activity[R]. Banco de Mexico, Working Papers, 2014
[5] Levanon G., Manini J. C., Ozyildirim A., et al. Using Financial Indicators to Predict Turning Points in the Business Cycle:The Case of the Leading Economic Index for the United States[J]. International Journal of Forecasting, 2015,31(2):426-445
[6] 王红云,李正辉.虚拟经济运行景气监测指标体系的设计[J].统计与决策, 2016,(4):4-8
[7] Stock J., Watson M. New Indexes of Coincident and Leading Economic Indicators[R]. NBER Macroeconomics Annual, 1989
[8] 王金明.我国经济周期波动对通货膨胀的动态影响——基于合成指数的实证研究[J].金融研究, 2012,(3):57-67
[9] 韩艾,郑桂环,汪寿阳.广义动态因子模型在景气指数构建中的应用——中国金融周期景气分析[J].系统工程理论与实践, 2010,30(5):803-811
[10] Kamada K., Nasu K. The Financial Cycle Indexes for Early Warning Exercise[R]. Bank of Japan Working Paper, 2011
[11] 邓创,徐曼.中美金融周期的协动性及其传导途径分析[J].世界经济研究, 2015,(11):12-20
[12] Paap R., Dijk D. V. Do Leading Indicators Lead Peaks more than Troughs?[J]. Journal of Business&Economic Statistics, 2009,27(4):528-543
[13] Camacho M., Perez-Quiros G., Poncela P. Extracting Nonlinear Signals from Several Economic Indicators[J]. Journal of Applied Econometrics, 2015,30(7):1073-1089
[14] 陈守东,孙彦林,刘洋.中国金融状况周期波动特征及趋势周期分解[J].科技促进发展, 2015,11(5):607-612
[15] Galati G., Hindrayanto I., Koopman S. J., et al. Measuring Financial Cycles in a Model-Based Analysis:Empirical Evidence for the United States and the Euro Area[J]. Economics Letters, 2016,145(8):83-87
[16] Frale C., Marcellino M., Mazzi G. L., et al. Survey Data as Coincident or Leading Indicators[J]. Journal of Forecasting, 2010,29(1-2):109-131
[17] 叶光.基于混频数据的一致指数构建与经济波动分析[J].统计研究, 2015,32(8):17-26
[18] Bora?anAruoba S., Diebold F. X., Scotti C. Real-Time Measurement of Business Conditions[J]. Journal of Business&Economic Statistics, 2009,27(4):417-427
[19] 郑挺国,王霞.中国经济周期的混频数据测度及实时分析[J].经济研究, 2013,(6):58-70
[20] Camacho M., Quirós G. P., Poncela P. Green Shoots and Double Dips in the Euro Area:A Real Time Measure[J]. International Journal of Forecasting, 2014,30(3):520-535
[21] Mariano R. S., Murasawa Y. A Coincident Index, Common Factors, and Monthly Real GDP[J]. Oxford Bulletin of Economics and Statistics, 2010,72(1):27-46
[22] Camacho M. Mixed-frequency VAR Models with Markov-switching Dynamics[J]. Economics Letters, 2013,121(3):369-373
[23] Kim C. J., Nelson C. R. State-Space Models with Regime Switching:Classical and Gibbs-Sampling Approaches with Applications[M]. Cambridge:MIT Press Books, 1999
[24] 高铁梅.计量经济分析方法与建模:EViews应用及实例-第2版[M].北京:清华大学出版社, 2009