COMPARATIVE PERFORMANCE OF ESTAR AND AFRIMA MODELS IN FORECASTING THE NIGERIAN EXCHANGE RATE.
Abstract
This study examines and compares the predictive performance of the Exponential Smooth
Transition Autoregressive (ESTAR) and Autoregressive Fractionally Integrated Moving Average
(ARFIMA) frameworks for modelling and forecasting Nigeria’s exchange rate dynamics. Using
monthly observations spanning January 2000 to December 2025, the study investigates whether
exchange rate behaviour is better captured by nonlinear adjustment mechanisms or long-memory
dependence structures. Preliminary time-series diagnostics indicate evidence of persistence,
gradual adjustment toward equilibrium, and nonlinear characteristics in the underlying data-
generating process, suggesting that exclusive reliance on conventional linear specifications may
be inadequate. The competing models were estimated and assessed using both in-sample
adequacy and out-of-sample forecasting criteria. Model selection and forecast evaluation
employed the Akaike Information Criterion (AIC), Schwarz Information Criterion (SIC), Root
Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE). The empirical
results indicate that the ESTAR specification achieves superior short-term forecasting
performance, reflecting its capacity to capture regime-dependent movements and nonlinear
correction dynamics in exchange rate fluctuations. Conversely, the ARFIMA model exhibits
greater forecast stability over longer horizons, consistent with its ability to accommodate
fractional persistence and long-range dependence. The findings underscore the importance of
incorporating nonlinear and long-memory econometric structures into exchange rate forecasting,
particularly in emerging market contexts characterised by structural adjustments and market
frictions. By combining nonlinear transition modelling with long-memory representation, the
study provides empirical evidence that may strengthen forecasting practice and inform
macroeconomic surveillance, monetary policy formulation, and exchange-rate risk assessment in
Nigeria.
