Statistics and risk analysis on stock markets in Shanghai and Shenzhen
Yuepeng Chen · Journal of Huanggang Normal University · 2007
According to stochastic theory,the returns of stock market should obey normal distribution.However,much study shows financial time series,such as stock index returns,are of high peaks and heavy tails.Extreme value distribution and Laplace distribution are heavy-tailed distributions.Gumbel distribution and Laplace distribution are fitted to stock index returns from stocks in Shanghai and Shenzhen.The estimations of value at risk for the stock returns are computed.The statistical result indicates that Laplace distribution is better than normal distribution,and Gumbel distribution can quite accurately estimate the risk of large profit(extreme events).