Menu Content/Inhalt
Seminars Print
previous year previous month next month next year
See by year See by month See by week See Today Search Jump to month
Lada Kyj, Humboldt Print
Thursday, 22 October 2009, 12:15 - 13:15

A Blocking and Regularization Approach to High Dimensional Realized Covariance Estimation

Lada Kyj, Humboldt University, Berlin

We introduce a two-step blocking and regularization approach for the estimation of high-dimensional covariances using high-frequency data. In a first step, we apply a data-driven blocking scheme to order assets according to their observation frequencies and estimate the covariance matrix block-wise using realized kernels based on multiple time scales. In a second step, the covariance matrix is regularized using random matrix theory. The resulting estimator is positive-definite, well-conditioned and more efficient than the standard (non-blocking) realized kernel estimator by Barndorff-Nielsen, Hansen, Lunde, and Shephard (2008). The performance of the new estimator is analyzed in an extensive simulation study mimicking the liquidity and market microstructure features of the S&P 1500 universe. The blocking and regularization procedure yields significant efficiency gains for varying liquidity settings, noise-to-signal ratios, and dimensions. An empirical application to the estimation of daily covariances of the S&P 500 index confirms the simulation results.

Location: S 12.227
Contact: Claude Adan, This e-mail address is being protected from spam bots, you need JavaScript enabled to view it