运用贝叶斯方法的混合异方差模型的参数估计
|
摘要
介绍了混合正态广义自回归条件异方差模型的基本特征,推导出在风险中性测度下模型的变化。用贝叶斯方法进行参数估计,从而形成一种新的组合方法。利用上证50ETF2017. 01—2017. 12的历史数据进行实证分析,结果表明:采用这种新的组合方法对收益率时间序列数据进行估计,不仅可以有效地估计出模型的参数,而且在应用于我国上证5OETF期权时误差效果也比较好。
This paper introduces the characteristics of the mixed normal generalized autoregressive conditional heteroscedasticity model,and derive the changes of the model under the risk neutrality measure,and uses the Bayesian method to estimate the parameters,thus forming a new combination method. We use Shanghai stock 50 ETF from 2017. 01 to 2017. 12 to do the empirical analysis. The results show that using the combined method of return time series data to estimate can not only effectively estimate the parameters of the model,but also improve the error effect when applied to the Shanghai stock 50 ETF option in China.
This paper introduces the characteristics of the mixed normal generalized autoregressive conditional heteroscedasticity model,and derive the changes of the model under the risk neutrality measure,and uses the Bayesian method to estimate the parameters,thus forming a new combination method. We use Shanghai stock 50 ETF from 2017. 01 to 2017. 12 to do the empirical analysis. The results show that using the combined method of return time series data to estimate can not only effectively estimate the parameters of the model,but also improve the error effect when applied to the Shanghai stock 50 ETF option in China.
引文
[1] ENGLE R F,BOLLERSLEV T. Modeling the Persistence of Conditional Variances[J]. Econometric Reviews,1986,5:1-50.
[2] BOLLERSLEV T. Generalized Autoregressive Conditional Heteroscedasticity[J]. Journal of Econometrics,1986,31:307-327.
[3] WONG C,LI W. On a Mixture Autoregressive Conditional Heteroscedastic Model[J]. Journal of the American Statistical Association,2001,96:982-995.
[4] BAUWENS L,ROMBOUTS J. Bayesian Clustering GARCH Models[J]. Econometric Reviews,2007,26:365-386.
[5] CHIB S,NARDARI F,SHEPHARD N. Markov chain Monte Carlo methods for stochastic volatility models[J].Journal of Econometrics,2002,108(2):281-316.
[6] GEWEKE J. Exact Predictive Densites in Linear with ARCH Disturbances[J]. Journal of Econometrics,1989:63-86.
[7] ACHDOU Y,PIRONNEAU O. Computational methods for option pricing[M]. Siam:[s. n.],2005.
[8]殷玲,唐杰. GARCH-M模型与我国沪深股市波动[J].江南大学学报,2002,1(2):56-58.
[9]曾慧芳.自回归条件异方差模型的贝叶斯分析及其应用研究[D].长沙:湖南大学,2007.
[10]付伟芳.基于稳定分布的GARCH模型的Bayes参数估计及其实证分析[D].上海:华东师范大学,2007.
[2] BOLLERSLEV T. Generalized Autoregressive Conditional Heteroscedasticity[J]. Journal of Econometrics,1986,31:307-327.
[3] WONG C,LI W. On a Mixture Autoregressive Conditional Heteroscedastic Model[J]. Journal of the American Statistical Association,2001,96:982-995.
[4] BAUWENS L,ROMBOUTS J. Bayesian Clustering GARCH Models[J]. Econometric Reviews,2007,26:365-386.
[5] CHIB S,NARDARI F,SHEPHARD N. Markov chain Monte Carlo methods for stochastic volatility models[J].Journal of Econometrics,2002,108(2):281-316.
[6] GEWEKE J. Exact Predictive Densites in Linear with ARCH Disturbances[J]. Journal of Econometrics,1989:63-86.
[7] ACHDOU Y,PIRONNEAU O. Computational methods for option pricing[M]. Siam:[s. n.],2005.
[8]殷玲,唐杰. GARCH-M模型与我国沪深股市波动[J].江南大学学报,2002,1(2):56-58.
[9]曾慧芳.自回归条件异方差模型的贝叶斯分析及其应用研究[D].长沙:湖南大学,2007.
[10]付伟芳.基于稳定分布的GARCH模型的Bayes参数估计及其实证分析[D].上海:华东师范大学,2007.