|
Activity Number:
|
407
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Wednesday, August 1, 2007 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Business and Economics Statistics Section
|
| Abstract - #308861 |
|
Title:
|
Covariance Estimation for Nonsynchronous High-Frequency Data with Microstructure Noise
|
|
Author(s):
|
Qiuyan Xu*+ and Rituparna Sen
|
|
Companies:
|
University of California, Davis and University of California, Davis
|
|
Address:
|
421 Russell Park Apt 2, Davis, CA, 95616,
|
|
Keywords:
|
Non-synchronicity ; Microstructure noise ; Random lead-lag estimator ; Bias-variance trade-off
|
|
Abstract:
|
The use of high frequency return data has led to dramatic improvements in both theoretical and applied financial research. Covariance estimators among multiple processes have been proposed (e.g., De Jong and Nijman (1997) and Hayashi and Yoshida (2004, 2005, et al.). We introduce a new estimator, a random lead-lag estimator (RLLE) that coincides with the Hayashi-Yoshida estimator in the case where the frequency equals one second. We study the performance of RLLE for non-synchronous data under a situation with microstructure noise, and we obtain the optimal estimator with good bias-variance trade-off. Our result is confirmed by simulation results.
|
