Multivariate Time Series Analysis and Forecasting of Staple Food Prices in Kaduna State, Nigeria Using Vector Autoregression and Vector Error Correction Models

• Author(s): Reuben Solomon
• Paper ID: 1709523
• Page: 1933-1942
• Published Date: 31-07-2025
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 9 Issue 1 July-2025

Abstract

In Nigeria, staple food prices have been increasingly volatile, posing significant challenges to food accessibility and affordability. This study analyzes the dynamics of staple food prices in Kaduna State, Nigeria, focusing on rice, maize, soybeans, cowpea, and sorghum, using time series data from 2017 to 2023. The analysis reveals a statistically significant increase in food prices, with a notable surge and heightened volatility observed in 2023. Seasonal fluctuations, influenced by planting and harvest cycles, are also observed, with prices generally lower from January to March and higher from August to October. The unit root tests suggest stationarity at the first difference, while cointegration and Granger-causality were found in the time series. This suggests the suitability of the Vector Error Correction Model (VECM), which proved better than the baseline Vector Autoregression (VAR) model. The VECM provides more accurate forecast, with an overall average improvement of 4% in Mean Absolute Percentage Error (MAPE), 103 versus 131 in Mean Absolute Error (MAE) and 118 versus 150 in Root Mean Square Error (RMSE) for VECM and VAR respectively. The findings of this study contribute to a better understanding of staple food price dynamics in Kaduna State, providing valuable insights for policymakers and stakeholders seeking to enhance food security and affordability.

Citations

IRE Journals:
Reuben Solomon "Multivariate Time Series Analysis and Forecasting of Staple Food Prices in Kaduna State, Nigeria Using Vector Autoregression and Vector Error Correction Models" Iconic Research And Engineering Journals Volume 9 Issue 1 2025 Page 1933-1942

IEEE:
Reuben Solomon "Multivariate Time Series Analysis and Forecasting of Staple Food Prices in Kaduna State, Nigeria Using Vector Autoregression and Vector Error Correction Models" Iconic Research And Engineering Journals, 9(1)