Empirical Analysis On High-order Moment Asset Pricing Model Based On Quantile Regression

China has witnessed the 30 years of its stock market development.The scale of financing continues to improve,and the market is increasingly active,which has had an important impact on China's economic development.It is affected by macroeconomic environment,policy environment and investor behaviors and many other factors.For example,in 2008 and 2015 stock market disasters,the stock market fluctuated violently,and the yield of stock market didn't follow the normal distribution,but appears the property as "the peak,thick end".Based on the current situation of China's stock market,it is of great practical significance to find the factors affecting stock returns,establish asset pricing model,and analyze the relationship between stock returns and the high order moment factors and other influencing factors.The research contents of this paper include:(1)A comprehensive and systematic review of the theoretical development and practical application of asset pricing model.(2)We established a three-factor moment asset pricing model with higher moments.(3)The sample covered 10 years from 2008 to 2017 as the research interval and 3485 listed companies in Shenzhen Stock Exchange and Shanghai Stock Exchange as the research object.We used the least squares method and quantile regression method to analyze the change rule of the influence of "three factors" and "high-order moment" on the return on assets of stock market.The main conclusions are as follows:(1)The three factors can explain part of the return in China's stock market,but their respective explanatory power is different.The contribution of market premium factor and book-to-market value ratio factor to the model is significant,but the size factor has weak explanatory ability to the model.The goodness of fit of the whole model is also imperfect.Therefore,the explanatory ability of Fama-French three-factor model to China's stock market is not ideal and needs to be optimized.(2)High-order moments can not fully explain the volatility of stock market returns in China.The explanatory power of volatility and skewness in Chinese stock market has been verified to a certain extent,and the kurtosis factor needs more verification.(3)The explanatory power of high order moments on the volatility of stock market returns in different quantiles is different.Coskewness has a significant positive effect on yield,especially at high and low levels,and has a smaller effect at middle levels.The coefficient of Cokurtosis is negative in low levels,positive in high levels and not significant in middle levels.On this basis,some suggestions are put forward in order to help investors make better investment decisions and asset allocation decisions,and to provide a basis for government regulation.