Portfolio Construction by Volatility Forecasts: Does the Covariance Structure Matter?

This paper explores the performance of a global minimum variance (GMV) portfolio in dependence of the structure of the covariance matrix and the type of volatility model. We investigate quantitative portfolio strategies based on patterns of the covariance matrix, especially a diagonal covariance structure. Additionally, univariate and multivariate GARCH forecasts are explored to find optimal and cost minimizing weights for a portfolio consisting of the North America, Europe and the Pacific region. We find that variance forecasts are more important than covariance forecasts and that multivariate volatility models yield better results than univariate volatility models.