This paper examines the risk-return trade-off in the Australian Securities Exchange (ASX) using high-frequency data of related assets traded in other markets, where intra-day data are available while the ASX is closed. We consider the S&P/ASX 200 index and the ASX risk-neutral option-implied volatility (VIX) to highlight the importance of overnight information in predicting future index returns. Further, aside from the well-specified traditional approach of monitoring risk-return regressions using the second moment (volatility), we conjointly account for other higher-order moments such as the third and the fourth moments (skewness and kurtosis) to investigate the impact of overnight information corrected moments on predicting the future returns using the cointegrated fractional VAR (CFVAR) model. We find that the monthly compounded realized volatility and realized skewness adjusted with the fractional integration parameter are significantly negatively and positively related with the subsequent monthly returns, respectively. Moreover, the multivariate setting of our study implies that there exists a cointegrating relationship between the realized volatility and VIX, which can be regarded as the variance risk premium.
- Australian Securities Exchange (ASX)
- CFVAR model
- High frequency
- Overnight volatility