Modelling and forecasting of Nigeria stock market volatility

Abstract This study models and forecasts the volatility of the Nigerian Stock Exchange (NSE) using advanced econometric techniques, focusing on examining the asymmetric volatility and the leverage effect. Daily data from the NSE All Share Index spanning from 30 th January, 2012, to 16 th October, 2024 (3,176 days) are analysed using generalized autoregressive conditional heteroskedasticity family models, including EGARCH and GJR-GARCH, along with non-Gaussian distributions like the Student’s t-distribution. The findings reveal a significant leverage effect, where negative shocks impact stock prices more than positive ones, supporting asymmetric volatility theory. The study also identifies volatility clustering, where high-volatility periods are followed by continued volatility, further highlighting the persistence of market turbulence. Among the models tested, GJR-GARCH with the Student’s t-distribution performs best in forecasting volatility, providing superior fit and forecasting accuracy. These insights offer practical implications for investors and policymakers in managing risks in emerging markets, particularly during periods of high volatility.