MODELING AND FORECASTING VOLATILITY DYNAMICS IN THE NIGERIAN EQUITY MARKET: AN AR–GARCH

This paper analyses the volatility properties and forecasting performance of the Nigerian Stock Index (NSI) using monthly data from January 2000 to December 2025. The AR(1)-GARCH(1,1) model is estimated using Maximum Likelihood Estimation and selected based on the Log-Likelihood, Akaike Information Criterion, Schwarz Information Criterion and Hannan-Quinn Information Criterion. Forecast performance is evaluated using Root Mean Square Error, Mean Absolute Error, Mean Absolute Percentage Error and Theil's Inequality Coefficient for both in-sample and out-of-sample forecasts. Robustness is assessed using Student-t innovations, alternative GARCH specifications, pre- and postCOVID-19 sub-period analyses, and additional diagnostic measures. The results reveal significant volatility clustering, persistence, and conditional heteroskedasticity. Overall, the AR(1)-GARCH(1,1) model provides the most parsimonious, statistically adequate, and robust framework for modelling and forecasting Nigerian stock market volatility, offering valuable evidence for portfolio optimisation, financial risk management, investment planning, and policy formulation in Nigeria under varying market conditions and periods of economic uncertainty alike.