Forecasting Volatility States and Active Portfolio Strategies

In this paper, we analyze the value of predicting index returns as well as volatility. On the basis of a three state regime-switching model we produce genuine out-of-sample forecasts for the volatility of the Samp;P 500. Using monthly data from 1900 to 1999, we test the statistical significance of return and volatility timing for mean-variance investors. We find strong evideince for market timing in both returns and volatility. Furthermore, adding the possibility of leverage do not add anything to the relationship between risk and return in the portfolios