Arima And ETS Model Performance for Forecasting Nigeria Crude Oil Price

Abstract

This study investigates the effectiveness of the Autoregressive Integrated Moving Average (ARIMA) and Exponential Smoothing State Space (ETS) models in forecasting Nigeria’s crude oil prices using a time series approach. Monthly crude oil spot prices from January 2009 to May 2024, obtained from the Central Bank of Nigeria, served as the dataset. Descriptive analysis revealed significant volatility in oil prices over the study period, with prices ranging from $14.28 to $130.10. A time plot and decomposition analysis indicated a strong upward trend and minimal seasonal effects, supported by a calculated trend strength of 0.922 and seasonal strength of 0.05. Stationarity testing using the Augmented Dickey-Fuller test confirmed that first differencing was necessary to stabilize the series.