论文部分内容阅读
针对金融市场中跳跃特征的刻画问题,提出了贝叶斯跳跃厚尾随机波动模型。通过随机波动模型的结构分析和状态空间转换,设计了模型参数估计的MCMC算法,利用Kalman滤波和高斯模拟平滑方法估计模型的潜在波动,运用贝叶斯因子对随机波动类模型进行比较分析,并利用中国和美国的股市收益数据进行实证分析。研究结果表明:在刻画中、美两国股票市场的波动特征方面,跳跃厚尾随机波动模型要明显优于厚尾随机波动模型和标准随机波动模型,并且金融危机背景下的中国和美国股票市场都具有明显的波动持续性以及跳跃特征。
Aiming at the characterization of jumping features in financial markets, a Bayesian jump thick-tailed stochastic volatility model is proposed. Through the structural analysis and state space transformation of the stochastic volatility model, the MCMC algorithm for model parameter estimation is designed. The Kalman filtering and Gaussian simulation smoothing method are used to estimate the potential volatility of the model. The Bayesian factor is used to analyze the stochastic volatility model. Use China and the United States stock market earnings data for empirical analysis. The results show that the jump thick-tailed stochastic volatility model is significantly better than the thick tailed stochastic volatility model and the standard stochastic volatility model in depicting the volatility characteristics of the stock markets in the United States and the United States. In the context of the financial crisis, China and the United States stock markets Both have obvious volatility and jumping characteristics.