Authors:
Promise Saro Daewii, Nwikpe Barinaada John, Davis Iyai, Deebom Zorle Dum, Ogunyinka Ebunoluwa Adedayo
Addresses:
Department of Mathematics, Rivers State University, Port Harcourt, River State, Nigeria. Department of Statistics, Ignitus Ajuru University of Education, Port Harcourt, River State, Nigeria. Department of Mathematics, Rivers State Universal Basic Education Board, Port Harcourt, River State, Nigeria.
Abstract:
This study was conducted to investigate the impact of exogenous variables on stock price volatility. The performance of the classical GARCH model and GARCH-X models was compared using stock price data. The GARCH-X model incorporates two exogenous variables (exchange rate and interest rate), which allows it to account for external economic factors and asymmetries in the data. The study utilised daily stock prices, exchange rates, and interest rates from February 1, 2012, to February 5, 2024. The descriptive statistics revealed that the distributions of returns on the stock prices were skewed and leptokurtic. The result of the unit root test, conducted using the augmented Dickey-Fuller (ADF) test, indicated that the returns on the series were stationary. The ARCH LM-test detected the presence of ARCH effects, justifying the use of GARCH models. The mean equation was estimated, and the GARCH-X (1,1) model was fitted to the data, incorporating two exogenous variables (daily exchange rate and interest rate). The Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), Hannan-Quinn (HQ), Shibata, and Log-Likelihood were used to test the models’ goodness of fit. The study's findings revealed that GARCH-X (1,1) has the lowest AIC, BIC, and HQ compared to GARCH (1,1). Both models exhibit high persistence in volatility, with GARCH (1,1) at 0.98805 and GARCH-X (1,1) at 0.9989987, indicating that volatility shocks have prolonged effects. Furthermore, among the exogenous variables, δ1 was statistically significant at the 5% level (p = 0.0147), suggesting that the exchange rate has a significant effect on stock price volatility. However, δ2 was not significant (p = 0.0842), indicating that the interest rate does not have a significant impact on volatility within the model.
Keywords: Exogenous Variables; GARCH-X Model; Exchange Rate; GARCH and Volatility; Nigeria's Economy; Stock Market; Economic Stability; Macroeconomic Variables; Stock Volatility.
Received: 05/04/2024, Revised: 01/06/2024, Accepted: 23/07/2024, Published: 03/03/2025
DOI: 10.64091/ATIML.2025.000098
AVE Trends in Intelligent Management Letters, 2025 Vol. 1 No. 1 , Pages: 28-37