中国证券市场波动与收益的非线性相关

考察我国沪深两市指数收益的序列独立性.表明证券市场收益序列尽管线性自相关现象不显著,却存在着明显的非线性相关关系.而且这种非线性相关关系一般可由“ARCH效应”来加以解释,即波动聚类性是形成非线性相关的主要原因.应用BDS统计方法对收益残差的检验显示,GARCH(1,1)形式能够很好地刻画上证综合指数的非线性和波动性特征,ARCH(3)形式则能够很好地刻画深证综合指数的生成过程.

Volatility and Nonlinear Dependence in the Returns of China's Security Markets

We investigate the serial dependence of the returns of the Shanghai Composite Index and Shenzhen Component Index.Although the data exhibit no significantly linear autocorrelation,substantial evidence indicates the presence of nonlinear dependence.Further examination shows that the nonlinearities of the two return series are mainly due to autoregressive conditional heteroskedasticity(ARCH) effects,for each series will be independent after filtered through a certain ARCH model.