Modelling financial time series with threshold nonlinearity

Abstract

Financial markets are a system of complex price dynamics that are often influenced by various nonlinear factors. Traditional linear models such as Autoregressive Moving Average also known as ARMA and the GARCH model often fail to capture the inherent nonlinearities observed in financial market returns and trading volumes which poses significant problems in modelling financial time series. The aim of this study was to investigates the role of threshold nonlinearity in modelling financial market returns and trading volume. Daily share prices and trading volumes from the S&P 500 and the Nasdaq indices spanning from January 2000 to December 2020 were used as the sample financial markets. The findings revealed that the threshold model improves predictive performance over traditional linear models, highlighting the importance of incorporating nonlinearity for understanding the dynamics of financial markets. A threshold autoregressive model was proposed to account for sudden shifts in market conditions and nonlinear dependencies between returns and trading volumes.

Keywords: {'name': 'Threshold Nonlinearity, Returns, Trading Volume, Nonlinear Models, TAR Model'}

Authors & affiliations

Samuel Tabot Enow
Research Associate, The IIE VEGA School

Deposited references

Supplied references, not a list of publications citing this article.

DOI: 10.1016/j.cbrev.2018.11.002

DOI: 10.1017/bpp.2024.13

DOI: 10.1007/s11135-022-01605-4

DOI: 10.2307/2527343

DOI: 10.3390/jrfm16030187

DOI: 10.1111/j.1540-6261.2004.00661.x

DOI: 10.1016/j.jeconom.2016.09.005

DOI: 10.1007/s11336-013-9330-8

DOI: 10.1016/S0304-4076(01)00073-2

Elder, J., Kim, M., & Clements, A. (2002). Threshold autoregressive models and the nonlinearity of financial time series. Journal of Financial Econometrics, 6(3), 345–368.

DOI: 10.1198/073500104000000370

DOI: 10.47743/jopafl-2023-27-09

Enow, S. T. (2023). Exploring volatility clustering in financial markets and its implication. Journal of Economic & Social Development, 10(2), 81–85.

Fenton, N. E., & Godfrey, S. (2008). Risk assessment: Theory, methods, and applications. Wiley-Interscience.

DOI: 10.1093/rfs/5.2.199

Gómez, V., & Velasco, C. (2013). A comparison of threshold autoregressive models for volatility prediction. Journal of Time Series Analysis, 34(1), 94–116.

DOI: 10.1093/oso/9780198773191.001.0001

Hasbrouck, J., & Saar, G. (2009). Limit orders and liquidity on the NASDAQ market. Journal of Financial and Quantitative Analysis, 44(3), 553–578.

DOI: 10.1002/cpz1.801

Kaas, R., Goovaerts, M., Dhaene, J., & Denuit, M. (2000). Exponential claims reserving using the chain-ladder method. ASTIN Bulletin: The Journal of the IAA, 30(2), 143–167.

DOI: 10.1016/j.jbusres.2019.01.044

DOI: 10.1111/1468-0262.00071

DOI: 10.1080/01621459.1994.10476462

DOI: 10.1007/978-1-4684-7888-4

DOI: 10.1080/01621459.1998.10473779

DOI: 10.1016/j.ecolind.2023.110371