A study on the distribution of nonparametric volatilities based on Chinese stock market

In this article, we examine the distributions of four different nonparametric volatility measurements- Realized volatility, Realized Range-based Volatility, Realized Bipower Variation and Realized Absolute volatility using the high frequency data of Chinese Shanghai Securities Composite Index. Our empirical results show that the distributions of return series standardized by nonparametric volatility are nearly Gaussian distribution. By comparing these four nonparametric volatilities, we find that the Realized Range-based Volatility is a more efficient way to measure the volatility. The results also confirm that the nonparametric volatility can describe the dynamic behaviors of Chinese stock market well, which indicate that the Chinese stock market is weakly efficient.