Abstract

<p>The dynamic behavior in the prices of commodity particularly their interdependence, interaction and evolution, clearly cause shocks among themselves. However, this study is a multivariate time series modelling which investigates the interactions and pattern of causality using the unrestricted vector autoregressive (VAR) approach. Monthly data on the variables spanning from the period of January 2009 to December 2020 were extracted from the central bank of Nigeria (CBN) Statistical bulletin. The study used both the descriptive and analytical design. Preliminary investigation was conducted such as time plots and unit root test to determine the presence or absence of trend and unit root on the study variables. The unit root test shows that all the variables had a unit root at level I(0), while at first difference I(1) all the variables were stationary using the Augmented Dickey Fuller Test (ADFT) and Philip-Perron Test (PPT). The trace statistic and max eigen statistic results show no long memory relationship. The Akaike Information Criterion (AIC) shows a lag length of 2. The VAR estimate indicated that the variables were significantly affected by its first and second lags. The granger causality test indicated significant influence on each of the variables. The Wald statistics shows that both lags of each variables were jointly significant in affecting itself. The impulse response shows that all variables were rapidly affected by its own shocks, hence the study prohibited the response of interest rate to existing shocks in the price of groundnut oil and palm oil. The variance decomposition as well shows that at least 90% of the impulse response were from its own shocks. It was however, recommended that government should regulates interest rate and stabilized the price of commodities.</p>