Fear and Forecasting in Scandinavia : Implied Volatility Indices for the Scandinavian Equity Markets

Abstract

This thesis investigates the use of the model-based and model-free implied volatility index methodologies in Scandinavia from 2018 to 2023, leading to the creation of a composite index for the region: SCANDI-VIX. It confirms a significant negative contemporaneouss relationship between the Scandinavian implied volatility indices (NORVIX, DANVIX, SWEVIX, SCANDI-VIX) and their underlying index returns, validating their role as a "fear gauge." The study reveals an asymmetric response of these implied volatility indices to market returns, aligning with the leverage effect theory. We investigate the structural changes in the underlying market time-series as a consequence of the COVID-19 pandemic, and it’s implications for EGARCH forecasting. With a final key finding being the increased forecasting quality observed when utilising implied volatility as an input feature in the Extreme Gradient Boosting (XGBoost) machine learning model.