Title :
Realized correlation of high-frequency data based fourier analysis
Author :
Zhang, Jie ; Wang, Zhuo ; Zhai, Dongsheng
Author_Institution :
Econ. & Manage. Sch., Beijing Univ. of Technol., Beijing, China
Abstract :
Financial high-frequency data are not equally spaced, standard correlation measures such as Realized Correlation can not be directly applied to the raw data which have to be homogenized by interpolating. Fourier-Realized Correlation is a method which uses all the tick-by-tick data with no need to change their structure. In this paper, Fourier-Realized Correlation of stock returns, the efficiencies of the two methods are compared. Empirical results show that Fourier-Realized Correlation is a better choice in terms of stability.
Keywords :
Fourier analysis; data structures; financial data processing; Fourier-realized correlation; financial high-frequency data; high-frequency data based Fourier analysis; realized correlation; stock returns; Data analysis; Frequency domain analysis; Frequency estimation; Frequency measurement; Interpolation; Length measurement; Measurement standards; Sampling methods; Time measurement; Time series analysis; Correlation measure; Fourier-Realized Correaltion; High-frequency data;
Conference_Titel :
Information Management and Engineering (ICIME), 2010 The 2nd IEEE International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4244-5263-7
Electronic_ISBN :
978-1-4244-5265-1
DOI :
10.1109/ICIME.2010.5477852