MODELLING THE NIGERIAN STOCK EXCHANGE SERIES USING EVENT-  BASED ARIMAX MODEL

A. A. Akintunde; B. O. Adetona; K. R. Ampitan; N. O. Ogunnusi; S. B. Akanni; O. R. Aina,; F. I. Akintunde

A. A. Akintunde Department of Statistics, Federal University of Agriculture Abeokuta, Nigeria.
B. O. Adetona Department of Statistics, Federal University of Agriculture Abeokuta, Nigeria.
K. R. Ampitan Department of Statistics, Federal University of Agriculture Abeokuta, Nigeria.
N. O. Ogunnusi Department of Mathematics and Statistics, Federal Polytechnic, Ilaro, Nigeria
S. B. Akanni Department of Mathematical Sciences, Crescent University, Abeokuta, Nigeria
O. R. Aina, Department of Statistics, Federal University of Agriculture Abeokuta, Nigeria.
F. I. Akintunde Department of Statistics, Federal University of Agriculture Abeokuta, Nigeria.

Keywords: Time series analysis, ARIMA model, event-based ARIMAX model, Exogenous variable, seasonal ARIMAX,

Abstract

Current investigation looked into dynamics of the Nigerian Stock Exchange with the aid of time
series modeling techniques. The All-share index was adopted, with a specific focus on
incorporating major economic and political events through event-based ARIMAX models.
Weekly ASI data were collected and subjected to analysis and diagnostic checks. The series was
differenced to achieve stationarity, and ARIMAX models were fitted. Notably, exogenous
variables such as the COVID-19 pandemic, the 2023 general elections, and the removal of fuel
subsidy in 2023 were encoded as dummy variables and integrated into the ARIMAX model.
Multicollinearity diagnostics using the Variance Inflation Factor (VIF) indicated no serious
multicollinearity among the exogenous variables. Comparison was achieved using the Akaike
Information Criterion (AIC). The result revealed that the ARIMAX model with lagged event
dummies provided improved explanatory power over the standard ARIMA model. Residual
diagnostics including the Ljung-Box test confirmed the models’ adequacy. Macroeconomic
shocks on market behavior and the usefulness of incorporating event-based structures in time
series forecasting can be seen to be of great significance from the obtained results.