On the Efficient and Optimal Predictive Values for Economic Growth with Covariate Predictors: Ordinary Least Square and Ridge Regression Approach

Abstract

This study examined an efficient and optimal estimate and predicted value for economic growth using the explanatory variables that include internal and external debts, interest and exchange rate, and trade openness, which were correlated to cause a multicollinearity problem. The ordinary least square and ridge regression (RR) technique were adopted to analyze data gathered from the Central Bank of Nigeria (1986–2022). The diagnostic test conducted using the variance inflation factor revealed that the ordinary least square technique established a multicollinearity problem, which was addressed when the RR method was used with an appropriate ridgeconstant. The predictive performance metrics such as root mean square error, the mean absolute error, the mean absolute percentage error, and the bias proportion for the fitted RR were smaller when compared with the values obtained using the ordinary least square regression technique. Consequently, an RR was chosen as the most efficient and optimal technique to predict stable and reliable values for the economic growth. Therefore, this study was beneficial to the policymakers because it provided the needed understanding that captured the contributions of the identified economic growth drivers. The negative influence of the external debt on the economic growth was not in doubt. In addition, this study was significantly beneficial to the researchers by strengthening their understanding of the appropriate estimation technique to be adopted for efficient, optimal, stable, and reliable predictive values in the presence of multicollinearity.

Received: 7 March 2025 | Revised: 22 July 2025 | Accepted: 11 November 2025

Conflicts of Interest

The author declares that he has no conflicts of interest to this work.

Data Availability Statement

The data that support the findings of this study are openly available in the Central Bank of Nigeria Statistical Bulletin via the link:

https://www.cbn.gov.ng

Author Contribution Statement

Ebiwonjumi Ayooluwade: Conceptualization, methodology, software, validation, formal analysis, Iinvestigation, resources, data curation, writing – original draft, writing – review & editing, vsualization, supervision, project administration.