Properties of Bias-Corrected Realized Variance Under Alternative Sampling Schemes

Posted: 29 Feb 2008

See all articles by Roel C. A. Oomen

Roel C. A. Oomen

Deutsche Bank AG (London); London School of Economics & Political Science (LSE) - Department of Statistics

Multiple version iconThere are 2 versions of this paper

Date Written: 2005

Abstract

In this article I study the statistical properties of a bias-corrected realized variance measure when high-frequency asset prices are contaminated with market microstructure noise. The analysis is based on a pure jump process for asset prices and explicitly distinguishes among different sampling schemes, including calendar time, business time, and transaction time sampling. Two main findings emerge from the theoretical and empirical analysis. First, based on the mean-squared error (MSE) criterion, a bias correction to realized variance (RV) allows for the more efficient use of higher frequency data than the conventional RV estimator. Second, sampling in business time or transaction time is generally superior to the common practice of calendar time sampling in that it leads to a further reduction in MSE. Using IBM transaction data, I estimate a 2.5-minute optimal sampling frequency for RV in calendar time, which drops to about 12 seconds when a first-order bias correction is applied. This results in a more than 65% reduction in MSE. If, in addition, prices are sampled in transaction time, a further reduction of about 20% can be achieved.

Keywords: bias correction, diffusion limit, market microstructure noise, optimal sampling, pure jump process, realized variance

Suggested Citation

Oomen, Roel C.A., Properties of Bias-Corrected Realized Variance Under Alternative Sampling Schemes ( 2005). Journal of Financial Econometrics, Vol. 3, Issue 4, pp. 555-577, 2005. Available at SSRN: https://ssrn.com/abstract=821760

Roel C.A. Oomen (Contact Author)

Deutsche Bank AG (London) ( email )

Winchester House
1 Great Winchester Street
London, EC2N 2DB
United Kingdom

London School of Economics & Political Science (LSE) - Department of Statistics ( email )

Houghton Street
London, England WC2A 2AE
United Kingdom

Register to save articles to
your library

Register

Paper statistics

Abstract Views
668
PlumX Metrics