A Factor-Based Estimation of Integrated Covariance Matrix With Noisy High-Frequency Data

Abstract

This article studies a high-dimensional factor model with sparse idiosyncratic covariance matrix in continuous time, using asynchronous high-frequency financial data contaminated by microstructure noise. We focus on consistent estimations of the number of common factors, the integrated covariance matrix and its inverse, based on the flat-top realized kernels introduced by Varneskov. Simulation results illustrate the satisfactory performance of our estimators in finite samples. We apply our methodology to the high-frequency price data on a large number of stocks traded in Shanghai and Shenzhen stock exchanges, and demonstrate its value for capturing time-varying covariations and portfolio allocation.

Keywords:

• High-dimensional covariance matrix
• Portfolio selection
• Principal orthogonal complement thresholding estimator
• Principle component analysis
• Realized kernels

Supplementary Materials

The supplementary materials include the proofs for the main theoretical results of this article, the additional simulation results and the code used to implement our methods.

Acknowledgments

We are grateful to the editor, the associate editor, and two anonymous referees for their useful comments. We also benefit from helpful discussions with Kunpeng Li, Liangjun Su, Xia Wang, and Christian Brownlees.

Additional information

Funding

The authors gratefully acknowledge the financial support from NSFC No. 71991470 and No. 71991471.