Modelling the Nigeria Crude Oil Prices Using ARIMA, Pre-intervention and Post-intervention Model

Main Article Content

Wiri, Leneenadogo
Tuaneh, Godwin Lebari

Abstract

The study applied Autoregressive Integrated Moving Average Intervention in modelling crude oil prices in Nigeria spanning the period from January 1986 to June 2017. The time plot of the series showed an abrupt increase in the series and this called for intervention modelling. The data was divided into three set (actual series, pre-intervention and post-intervention series). The Augmented Dickey Fuller (ADF) was used to test for unit root on each of the series and were all found to be non-stationary at levels, they (actual, pre and post- intervention series) were however non stationary at first difference. Eighteen models were estimated and the best model was the pre-intervention model that minimise the Akaike information criterion (AIC) (ARIMA (111)) with AIC of (4.4.578). The plot of the residual correlogram showed adequacy of the model. The model was adequate since there was no spike that cut the level of the correlogram and the histogram of the residual was normally distributed with probability values (0.0000).

Keywords:
ARIMA, pre- intervention, post-intervention, crude oil prices, Nigeria.

Article Details

How to Cite
Leneenadogo, W., & Lebari, T. G. (2019). Modelling the Nigeria Crude Oil Prices Using ARIMA, Pre-intervention and Post-intervention Model. Asian Journal of Probability and Statistics, 3(1), 1-12. https://doi.org/10.9734/ajpas/2019/v3i130083
Section
Original Research Article