We propose a joint modeling strategy for timing the joint distribution of the returns and their volatility. We do this by incorporating the potentially asymmetric links into the system of 'independent' predictive regressions of returns and volatility, allowing for asymmetric cross-correlations,...

We investigate the relationship between a mutual fund's variation in factor exposures and its future performance. Using a dynamic state space version of Carhart (1997)'s four factor model to capture factor variation, we find that funds with volatile factor exposures underperform funds with...