Energy use, carbon dioxide emissions, GDP, industrialization, financial development, and population, a causal nexus in Sri Lanka: With a subsequent prediction of energy use using neural network

ABSTRACT

The study examines the causal relationship between energy use, carbon dioxide emissions, GDP, industrialization, financial development, and population from 1971 to 2012 in Sri Lanka, using the ARDL regression analysis and a subsequent prediction of energy use using neural network. There was evidence of a long-run equilibrium relationship running from carbon dioxide emissions, GDP, industrialization, financial development, and population to energy use. The Granger causality test shows a unidirectional causality running from carbon dioxide emissions to energy use and a bidirectional causality between industrialization and energy use. The overall predicted EUSE from 1971 to 2012 has a mean absolute percentage error of 1.97%. Evidence from the neural network shows that the statistical coefficient of R-square for both training and validation is 98% and 99% with a corresponding Root mean square Error of 11.11 and 6.10, respectively.

KEYWORDS:

• carbon dioxide emissions
• econometrics
• energy economics
• neural network
• Sri Lanka

Notes

¹ “Industrial value added” is used as a proxy for “industrialization.”

² “Money and quasi-money” is used as a proxy for “financial development.”