主管:中国科学院
主办:中国优选法统筹法与经济数学研究会
   中国科学院科技战略咨询研究院

Chinese Journal of Management Science ›› 2014, Vol. 22 ›› Issue (1): 10-19.

• Articles • Previous Articles     Next Articles

Infinite Markov-switching VAR Model and Application to Analysis of China Stock Market Return

CAI Wei-hong1,2, TANG Qi-ming1   

  1. 1. School of Economics, Huazhong University of Science and Technology, Wuhan 430074, China;
    2. School of International Trade and Economics, Guangdong University of Foreign studies, Guangzhou 510006, China
  • Received:2012-02-24 Revised:2012-07-20 Online:2014-01-20 Published:2014-01-20

Abstract: A new Markov-switching VAR model is developed in which the number of the regimes is driven by data. The model is inferenced with Bayesian methods, and estimated with block sampling based MCMC method. With the studying of weekly return data of Shanghai A share market, five contrasted regimes are identified using the proposed model which are differenciated by return volatility. Before April 1992, market volatility is extremely low and since then there are two periods and three regimes are switching in each period.

Key words: infinite Markov-switching, VAR, Bayesian inference, block sampling, A share market return

CLC Number: