Research Of Threshold Generalized Hyperbolic Stochastic Volatility Model With Double Leverage And Its Application

Volatility is one of the indicators of financial market risk measurement,which can be used to describe the uncertainty of financial asset changes.And it is one of the important bases for people to consider when they invest in assets,buy financial products and predict financial risks.In order to capture the time-varying and multiple volatility characteristics of the financial market and its derivative markets,this paper constructs and extends the threshold generalized hyperbolic stochastic volatility model with double leverage,which is of great significance to enrich the theoretical research of the volatility market.Firstly,in order to fully describe the volatility characteristics of financial markets such as peaks and heavy tails,skewness and asymmetry,this paper introduces the threshold effect to the generalized hyperbolic skew student’s t-distribution stochastic volatility model.In addition,in order to capture the asymmetry of the positive and negative shocks of asset returns,this paper introduces leverage effect and assumes that the leverage parameters are state-related,so as to construct a threshold generalized hyperbolic skew student’s t-distribution stochastic volatility model with double leverage(GHST-THSV-DL)to fully describe the volatility characteristics of asset returns.At the same time,the asymmetry of bad news and good news is described in more detail.Afterwards,Bayesian analysis is carried out on the constructed model,and empirical research is carried out based on the integrated circuit index and the US Philadelphia semiconductor index.The research results show that the volatilities of the two markets have sharp peaks and heavy tails,high persistence and obvious leverage effects;the domestic IC market is vulnerable to bad news,while foreign IC market is more vulnerable to good news.Secondly,when affected by external disturbances such as market shocks and national policies,the volatility of financial markets may produce jumps.This paper extends the GHST-THSV-DL model,adding the double exponential jumps(DEJ)process to construct the GHST-THSV-DL-DEJ model.And with the help of event research method,we analyze the jumping of domestic and foreign stock markets.The results show that the GHST-THSV-DL-DEJ model not only better describes the jumping and time-varying volatility of the returns of the Shanghai Composite Index and the S&P 500 Index,but also in the economic sense,the strong jump phenomenon reflects the impact of financial policies and major events on the entire stock market in the current period.