c: AXA Investment Managers Preliminary and Incomplete

This paper assesses the relative economic value of volatility and correlation risk in the con-text of multivariate dynamic asset allocation strategies. Using exchange rate data, we model the dynamic covariance matrix of daily returns by implementing the multivariate Asymmetric Dynamic Conditional Correlation (ADCC) model of Cappiello, Engle and Sheppard (2006). Our statistical analysis develops a new Bayesian estimation algorithm for the ADCC model, provides a ranking of alternative model speci\u85cations in a way that accounts for parameter uncertainty, and constructs combined forecasts across a large set of correlation and volatility speci\u85cations using Bayesian Model Averaging. More importantly, we assess the economic value of volatility and correlation timing for the optimal portfolio decision of a risk averse investor in a dynamic mean-variance framework. We \u85nd that in foreign exchange markets there is substantial economic value in timing correlations in addition to the economic value of volatility timing; the former can add up to 350 basis points per annum to the 500 basis points of the latter. This result is ro-bust to reasonably high transaction costs as well as alternative volatility speci\u85cations, diagonal correlation structure and asymmetric correlations