Estimating High-Frequency Based (Co-) Variances: A Unified Approach

We propose a unified framework for estimating integrated variances and covariances based on simple OLS regressions, allowing for a general market microstructure noise specification. We show that our estimators can outperform, in terms of the root mean squared error criterion, the most recent and commonly applied estimators, such as the realized kernels of Barndorff-Nielsen, Hansen, Lunde & Shephard (2006), the two-scales realized variance of Zhang, Mykland & Ait-Sahalia (2005), the Hayashi & Yoshida (2005) covariance estimator, and the realized variance and covariance with the optimal sampling frequency derived in Bandi & Russell (2005a) and Bandi & Russell (2005b). For a realistic trading scenario, the efficiency gains resulting from our approach are in the range of 35% to 50%.