摘要
为了更准确地描述中国股市的周期波动,以上证综指和深证成指2001年1月12日到2016年12月23日的数据为样本,基于长记忆性和杠杆效应视角,运用MRS-APGARCH模型经验分析了中国股票市场的波动性。研究发现:沪深股市存在显著的三种波动状态,处于盘整状态的概率最大,平均持续时间最长;收益波动具有明显的时变长记忆性和非对称效应。所用估计方法显著提高了参数估计的精度和模型的拟合优度,所得结论为投资者构建有效的风险防范体系及投资决策提供了参考依据。
For the purpose of more comprehensive description of Chinese stock market volatility,using the data of Shanghai composite index and Shenzhen component index from January 12th,2001 to December 23rd,2016,the paper analyzed the volatility of Chinese stock markets with the MRS-APGARCH model. The results indicate that the two markets often act with three volatility states and the probability of mild violating is the highest. Volatility of stock returns has time-varying long memory and leverage effect. Compared with other literature,the paper improves the estimation of parameters. Empirical findings are of great importance for construction of risk defense system.
引文
[1]ENGLE R F.Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdominflation[J].Econometrica,1982,50:987-1007.
[2]BOLLERSLEV T.Generalized autoregressiveconditional heteroskedasticity[J].Journal of Econometrics,1986,31:307-327.
[3]HAMILTON J D.A new approach to the economic analysis of nonstationary time series and the business cycle[J].Econometrica,1989,57(2):357-384.
[4]ISMAIL M T,ISA Z.Identifying regime shifts in Malaysian stock market returns[J].International Research Journal of Finance and Economics,2008(15):44-57.
[5]WANG P,THEOBALD M.Regime-switching volatility of six East Asian emerging markets[J].Research in International Business and Finance,2008(22):267-283.
[6]HAMILTON J D,SUSMEL R.Autoregressive conditional heteroskedasticity and changes in regime[J].Journal of Econometrics,1994,64:307-333.
[7]CAI J.Markov model of unconditional variance in ARCH[J].Journal of Business and Economics Statistics,1994(12):309-316.
[8]GRAYS.F.Modeling the conditional distribution of interest rate as a regime-switching process[J].Journal of Financial Economics,1996,42:27-62.
[9]THIERRY A,LOREDANA U-R.Stock market dynamics in a regime-switching asymmetric power GARCH model[J].International Review of Financial Analysis,2006(15):109-129.
[10]赵华,蔡建文.基于MRS-GARCH模型的中国股市波动率估计与预测[J].数理统计与管理,2011,30(5):912-921.
[11]杨继平,张春会.基于马尔科夫状态转换模型的沪深股市波动率的估计[J].中国管理科学,2013,21(2):42-49.
[12]姜婷,周孝华,董耀武.基于Markov机制转换模型的我国股市周期波动状态研究[J].系统工程理论与实践,2013(8):1934-1939.
[13]KLAASSEN F.Improving GARCH volatility forecast with regimeswitching GARCH[J].Empirical Economics,2002(27):363-394.
[14]HENNEKE J S,RACHEV S T,FABOZZI F J,et al.MCMC-based estimation of Markov switching ARMA-GARCH models[J].Applied Economics,2011,43(3):259-271.
[15]BAUWENS L,PREMINGER A,ROMBOUTS J.Theory and inference for a Markov-switching GARCH model[J].Econometrics Journal,2010(13):218-244.
[16]HE Z,MAHEU J.Real time detection of structural breaks in GARCH models[J].Computational Statistics&Data Analysis,2010,54(11):2628-2640.
[17]BAUWENS L,DUFAYS A,ROMBOUTS J.Marginal likelihood for Markov-switching and change-point GARCH[J].Journal of Econometrics,2014,178:508-522.
[18]DUFAYS A.Infinite-state Markov-switching for dynamic volatility and correlation models[R].Belgium:CORE Discussion Paper,2012,1-37.
[19]MACIEJ A.Maximum likelihood estimation of the Markov-switching GARCH model[J].Computational Statistics and Data Anlysis,2014,76:61-75.
[20]DING Z,GRANGER W J.Modeling volatility persistence of speculative returns:A new approach[J].Journal of Econometrics,1996,73:185-215.
[21]王娟,李锐.MRS-GARCH模型在我国沪深股指波动中的应用研究[J].北京师范大学学(自然科学版),2015,51(5):484-491.