Back to Search Start Over

VC correlation analysis on the overnight and daytime return in Japanese stock market

Authors :
Tomoshiro Ochiai
Jose C. Nacher
Source :
Physica A: Statistical Mechanics and its Applications. 515:537-545
Publication Year :
2019
Publisher :
Elsevier BV, 2019.

Abstract

While most financial engineering and econophysics studies have focused in daytime trading, much less investigation has been devoted to the non-trading or night periods. In this work, the correlation between overnight and daytime return (correlation ND) and the correlation between daytime return and following over night return (correlation DF) were investigated, which led to several findings. First, a weak negative correlation between overnight and daytime return (correlation ND) was observed in Japanese Stocks Market. Secondly, the application of Volatility Constrained correlation (VC correlation) method led to a significant amplification of this signal which benefits for increasing predictability of day time return compared to standard correlation. Furthermore, the analysis of the amplified signal derived from VC correlation for each stock revealed a linear scale relationship between the standard correlation and VC correlation. Therefore, this result indicates that by using the VC correlation, stronger correlation effect can be observed. Taking together, these findings suggest that the combination of VC approach with financial trading data over night paves the way to improve market predictability.

Details

ISSN :
03784371
Volume :
515
Database :
OpenAIRE
Journal :
Physica A: Statistical Mechanics and its Applications
Accession number :
edsair.doi...........6c8427300c8e57235c3d44c1a2949874