Impact of energy consumption and economic growth on CO2 emission using multivariate regression

Abstract In this study, the relationship of energy consumption, economic growth and carbon dioxide (CO2) emission is investigated in the context of the Environmental Kuznets Curve. The research focuses on seven oil-rich countries in the Middle East and North Africa (MENA) region, namely, Algeria, Bahrain, Iran, Kuwait, Oman, Qatar, and Saudi Arabia, over the period of 1995–2014. A quadratic model formulation is assumed for CO2 emission with respect to energy consumption and economic growth. Multivariate linear regression is utilized to assess whether the EKC can be confirmed or not. The aim is to investigate how CO2 emission is affected by energy consumption, GDP, and GDP2. This problem can be analyzed in a panel data format or a multivariate regression format. The former is widely used in econometrics and social sciences while the latter, unfortunately despite its theoretical equivalency, flexibility and ease of use, hasn't received enough attention. This study provides an awareness about the availability of other tools in analyzing similar problems. The EKC can be assumed as an experimental postulate, however, not properly checking underlying statistical assumptions can lead to disagreement results. This article provides a step-by-step guidance to properly analyze the problem in a multivariate regression format and check its assumptions. The relevant MATLAB commands are also presented throughout the manuscripts.