Modeling Nigerian stock exchange volatility with a novel sine-exponentiated Student's t GARCH framework
Journal of Statistical Sciences and Computational Intelligence · 16.05.2026 · 2 (2) · 441-455
DOI: 10.64497/jssci.196 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Statistical Sciences and Computational Intelligence, online erschienen am 16.05.2026. Verfasst von Aishatu Kaigama und 4 weiteren Autor:innen. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This study evaluated the performance of GARCH models with sine-exponentiated Student's t-distributed error innovations in predicting stock return volatility in the Nigerian Exchange Group (NGX). Aware of the weaknesses of conventional GARCH models based on Student's t innovations, this study proposes a novel hybrid error distribution that can capture heavy tails and cyclical volatility fluctuations common in emerging-market financial time-series data. Three GARCH models, namely GARCH (1,1), GARCH (1,2), and GARCH (2,1), were applied to NSE return data, and their performance was compared using simulation and empirical analyses, with measures such as AIC, BIC, MAE, MSE, and RMSE. Results suggest that GARCH (2,1) Case 1 is the overall most preferred model with greater fit and predictive power for simulation, and the GARCH (1,2) model with sine-exponentiated Student's t innovations has greater volatility forecast and model fit than alternative specifications in modeling volatility clustering, tail heaviness, and periodicity for NSE daily data sets. This means that the application of flexible models of innovation significantly improves risk analysis and market modeling in developing economies such as Nigeria.
Zitieren
APA
Kaigama, A., Bakari, H. R., Mohammed, Y. A., Chamalwa, H. A., & Isa, A. M. (2026). Modeling Nigerian stock exchange volatility with a novel sine-exponentiated Student's t GARCH framework. Journal of Statistical Sciences and Computational Intelligence, 2(2), 441-455. https://doi.org/10.64497/jssci.196
Vancouver
Kaigama A, Bakari HR, Mohammed YA, Chamalwa HA, Isa AM. Modeling Nigerian stock exchange volatility with a novel sine-exponentiated Student's t GARCH framework. Journal of Statistical Sciences and Computational Intelligence. 2026;2(2):441-455. doi:10.64497/jssci.196
BibTeX
@article{Kaigama2026,
author = {Kaigama, Aishatu and Bakari, Harun Rann and Mohammed, Yusuf Abbakar and Chamalwa, Hamidu Aliyu and Isa, Alhaji Modu},
title = {Modeling Nigerian stock exchange volatility with a novel sine-exponentiated Student's t GARCH framework},
journal = {Journal of Statistical Sciences and Computational Intelligence},
year = {2026},
volume = {2},
number = {2},
pages = {441--455},
doi = {10.64497/jssci.196}
}
EUVIMED