Stock Market Risk Analysis Based On SSE 50

At present,the investment value and risk of the domestic stock market are mostly determined by the P/E ratio,which is a measure of profitability based on earnings per share.The lower the P/E ratio,the stronger the profitability and the greater the investment value.Therefore,it has become a reference standard for investment analysis of investors.However,the application of P/E ratio in China’s stock market has obvious shortcomings and serious limitations.The premise of constructing P/E ratio index is to assume that the securities market is effective,and there is information asymmetry in China’s securities market;At the same time,China has a unique problem of non tradable shares;There are institutional drawbacks in the issuance of new shares in China,which makes the issue price of new shares on the high side;In addition,through the formula of P/E ratio index,it can be found that when EPS is negative,P/E ratio index is also negative,so it is inappropriate to use it to measure intrinsic value.Therefore,the method of analyzing the risk of China’s stock market needs to be further improved.According to the defect of measuring the risk of China’s stock market by the P/E ratio index,combined with the special situation of China,this paper selects the net assets per share of 50 constituent shares of Shanghai Stock Exchange from 2004 to2021,and uses the share capital as the weight to calculate the theoretical yield of Shanghai Stock Exchange 50 market.At the same time,according to the daily closing price of the 50 constituent stocks of Shanghai Stock Exchange,the actual market return rate is obtained after seasonal treatment.By analyzing the deviation between the theoretical return rate and the actual return rate of Shanghai Stock Exchange 50,the criteria for judging the stock market risk are proposed.At the same time,according to the significant difference between the actual rate of return and the theoretical rate of return,the risk environment of the stock market is divided.Then,combined with macro and micro factors,we selected GDP,CPI,consumer confidence index,investor confidence index,turnover rate and other indicators.Through correlation analysis and LASSO method,we screened the factors,observed the differences between the influencing factors of the theoretical rate of return and the actual rate of return,built an econometric model,and analyzed the relationship between the rate of return and the influencing factors.At the same time,according to the average absolute error,root mean square error and other indicators,ARIMA model,ARIMAX model,LSTM model and MIDAS mixing model are used to predict,analyze and compare the yield.Finally,according to the 90% confidence interval of the theoretical rate of return,a stock market risk early warning and supervision mechanism is constructed.The empirical results show that:(1)the actual return rate and theoretical return rate of Shanghai Stock Exchange 50 do not obey the normal distribution at the significance level of 0.05;Then,the p value obtained by using the nonparametric hypothesis test is less than 0.05,indicating that there is a significant difference between the theoretical yield and the actual yield of SSE 50 as a whole;(2)The state of the stock market can be divided by the intersection of the 90% confidence interval of the actual rate of return and the theoretical rate of return.In a bull market,the actual rate of return is greater than the upper bound of the 90% confidence interval of the theoretical rate of return,in a bear market,the actual rate of return is less than the lower bound of the 90% confidence interval of the theoretical rate of return,and in a shock state,the actual rate of return is within the 90% confidence interval of the theoretical rate of return;(3)There are significant differences between the factors that affect the theoretical rate of return and the actual rate of return.The former is mainly affected by consumer confidence index and the number of listed companies,while the latter is mainly affected by investor confidence index and turnover rate;(4)In terms of the model relationship between the yield and its influencing factors,through the analysis of average absolute error,average absolute percentage error and root mean square error,it is found that the prediction effect of MIDAS based on mixing variables on the theoretical yield and actual yield is significantly better than the traditional ARIMA model,ARIMAX model and LSTM model.The possible innovations of this study are:(1)Propose a new stock market risk judgment standard.According to the special situation of China’s stock market and the defects of the P/E ratio index,this paper proposes to define and judge the stock market risk by analyzing the volatility of the market’s actual return rate and theoretical return rate;(2)Build a stock market risk early warning mechanism and supervision mechanism.By constructing a 90% confidence interval for the theoretical return rate,the paper studies the relationship between the actual market return rate and its volatility,and establishes a dynamic risk early warning and supervision mechanism for the stock market.