Smoothing it Out: Empirical and Simulation Results for Disentangled Realized Covariances

Abstract

We study the class of disentangled realized estimators for the integrated covariance matrix of Brownian semimartingales with finite activity jumps. These estimators separate correlations and volatilities. We analyze different combinations of quantile- and median-based realized volatilities, and four estimators of realized correlations with three synchronization schemes. Their finite sample properties are studied under five data generating processes, in presence, or not, of microstructure noise, and under synchronous and asynchronous trading. The main finding is that synchronizing with previous tick interpolation combined with the pre-averaged version of disentangled estimators based on Gaussian ranks (for the correlations) and median deviations (for the volatilities) provide a precise, computationally efficient, and easy alternative to measure integrated covariances. A minimum variance portfolio application shows the superiority of this disentangled realized estimator in terms of numerous performance metrics.