MODELS FOR FORECASTING THE OIL VOLATILITY INDEX WITH INCORPORATION OF IV INDICES AND OTHER UNCERTAINTY INDICATORS

Abstract

This study aims to investigate the predictive performance of various factors of uncertainty on the oil volatility index (OVX) and to provide accurate and reliable OVX forecasts. The study focuses on two categories of indicators representing uncertainty: implied volatility (IV) indices and other economic, business, and geopolitical risk factors. Using the Mean Squared Predictive Error (MSPE), Mean Absolute Error (MAE), and Model Confidence Set (MCS) test, the study evaluates the forecasting performance of the implemented models and assesses the predictive abilities of the different uncertainty indicators. The results suggest that the model that incorporates the US Economic Policy Uncertainty (EPU) index outperforms the remaining models, with the EPU index showing improvement in the forecasting ability of a simple model that focuses on OVX as a target variable. The study concludes that, except for the EPU index, the predictive ability of the models is not enhanced by the inclusion of most of the factors of uncertainty investigated in this study. The out-of-sample period used in this study includes the period of the oil collapse between 2014 and 2016, which provides significant insight into the forecasting performance of the different models during particularly volatile periods