Direct Estimation of Lead–Lag Relationships Using Multinomial Dynamic Time Warping

This paper investigates the lead–lag relationships in high-frequency data. We propose multinomial dynamic time warping (MDTW) that deals with non-synchronous observation, vast data, and time-varying lead–lag. MDTW directly estimates the lead–lags without lag candidates. Its computational complexity...

Full description

Saved in:
Bibliographic Details
Published inAsia-Pacific financial markets Vol. 27; no. 3; pp. 325 - 342
Main Authors Ito, Katsuya, Sakemoto, Ryuta
Format Journal Article
LanguageEnglish
Published Tokyo Springer Japan 01.09.2020
Springer Nature B.V
Subjects
Data analysis
Econometrics
Economic Theory/Quantitative Economics/Mathematical Methods
Economics and Finance
Finance
International Economics
Macroeconomics/Monetary Economics//Financial Economics
Original Research
Warping
Lead–lag relationships
High frequency trading
C63
Dynamic time warping
C58
Online AccessGet full text

Cover

More Information
Summary:This paper investigates the lead–lag relationships in high-frequency data. We propose multinomial dynamic time warping (MDTW) that deals with non-synchronous observation, vast data, and time-varying lead–lag. MDTW directly estimates the lead–lags without lag candidates. Its computational complexity is linear with respect to the number of observation and it does not depend on the number of lag candidates. The experiments adopting artificial data and market data illustrate the effectiveness of our method compared to the existing methods.
ISSN:1387-2834
1573-6946
DOI:10.1007/s10690-019-09295-z