Title: Value-at-Risk prediction using option-implied risk measures
Abstract:This paper investigates the prediction of Value-at-Risk (VaR) using option-implied information obtained by the maximum entropy method. The maximum entropy method provides an estimate of the risk-neutr...This paper investigates the prediction of Value-at-Risk (VaR) using option-implied information obtained by the maximum entropy method. The maximum entropy method provides an estimate of the risk-neutral distribution based on option prices. Besides commonly used implied volatility, we obtain implied skewness, kurtosis and quantile from the estimated risk-neutral distribution. We find that using the implied volatility and implied quantile as explanatory variables significantly outperforms considered benchmarks in predicting the VaR, including the commonly used GARCH(1,1)-model. This holds for all considered VaR prediction models and VaR probability levels. Overall, a simple quantile regression model performs best for all considered VaR probability levels and forecast horizons.Read More
Publication Year: 2018
Publication Date: 2018-10-01
Language: en
Type: preprint
Access and Citation
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot