Improving the accuracy: volatility modeling and forecasting using high-frequency data and the variational component
Abstract: In this study, we
predict the daily volatility of the S&P CNX NIFTY market index of India
using the basic ‘heterogeneous autoregressive’ (HAR) and its variant. In doing
so, we estimated several HAR and Log form of HAR models using different
regressor. The different regressors were obtained by extracting the jump and
continuous component and the threshold jump and continuous component from the
realized volatility. We also tried to investigate whether dividing volatility
into simple and threshold jumps and continuous variation yields a substantial
improvement in volatility forecasting or not. The results provide the evidence
that inclusion of realized bipower variance in the HAR models helps in
predicting future volatility.
Author: Manish Kumar
Journal Code: jptindustrigg100014
