论文部分内容阅读
本文先对上证指数收益率时间序列做非线性检测,再对时间序列进行结构性变化检测,发现上证指数收益序列既是非线性时间序列又有结构性变化;通过构建一个3状态,3阶滞后的异方差马尔可夫切换模型对1990年12月21日至2008年8月22日上证指数周收益率时间序列规律进行了实证分析,采用极大似然估计法对模型参数进行估计,识别出股市波动的三种主要的状态:慢涨、慢跌和快涨;实证结果表明马尔可夫切换模型能够比较有效的刻画股市波动的阶段性特征。
This paper firstly conducts a non-linear test on the time series of the yield of Shanghai Stock Index, and then conducts a structural change detection on the time series. It finds that the yield series of the Shanghai Composite Index is not only a nonlinear time series but also a structural change. By constructing a 3-state, Heterosceride Markov Switching Model Empirical Analysis of the Time Series of the Weekly Return Rate of the Shanghai Composite Index from December 21, 1990 to August 22, 2008 Using the Maximum Likelihood Estimation Method to Estimate the Model Parameters and Identify the Stock Market The three main states of volatility are slow rising, slow falling and rapid rising. The empirical results show that the Markov switching model can effectively characterize the stage characteristics of the stock market volatility.