doi: 10.1093/rof/rfr024 Modeling Market Downside Volatility*

Abstract. We propose a new methodology for modeling and estimating time-varying downside risk and upside uncertainty in equity returns and for assessment of risk–return trade-off in financial mar-kets. Using the salient features of the binormal distribution, we explicitly relate downside risk and upside uncertainty to conditional heteroskedasticity and asymmetry through binormal GARCH (BiN-GARCH) model. Based on S&P 500 and international index returns, we find strong empirical support for existence of significant relative downside risk, and robust positive relationship between relative downside risk and conditional mode