ENHANCING VOLATILITY FORECASTING IN THE NIGERIAN STOCK MARKET USING GARCH MODELS WITH ADVANCED INNOVATION DENSITIES

Abstract

This study investigates the role of advanced innovation densities in improving volatility
forecasting accuracy in the Nigerian stock market. Using daily All Share Index (ASI) data
spanning 2012 to 2023, the study applies GARCH-type models, including GARCH (1,1),
EGARCH (1,1), and APARCH (1,1), under multiple error distributions such as Normal,
Student-t, Generalized Error Distribution (GED), and their skewed variants. Preliminary
analyses confirm the presence of volatility clustering, non-normality, and ARCH effects in the
return series. Model parameters are estimated using Maximum Likelihood Estimation (MLE),
while forecasting performance was evaluated using Root Mean Square Error (RMSE).
Empirical findings reveal that models incorporating heavy-tailed and skewed innovation
densities significantly outperform the conventional normal distribution in forecasting
volatility. In particular, the APARCH (1,1) model with GED innovation density demonstrates
superior predictive performance, capturing extreme market fluctuations more effectively. This
results once again underscore the importance of selecting appropriate innovation densities in
volatility modelling, especially in emerging markets characterized by structural instability
and frequent shocks. The study provides valuable insights for investors, risk managers, and
policymakers seeking to improve forecasting accuracy and enhance financial decision
making.