This paper examines the impact of natural gas consumption, real gross fixed capital formation and trade on the real GDP in the case of Tunisia over the period 1980-2010. We use an Autoregressive Distributed Lag (ARDL) bounds testing approach to test for cointegration between the variables. The Toda-Yamamoto approach is then used to test for causality. Our findings indicate the existence of a long-term relationship between the variables. Natural gas consumption, real gross fixed capital formation and trade add in economic growth. Natural gas consumption, real gross fixed capital formation and real trade cause real GDP in Tunisia. These findings open up new insights for policymakers to formulate a comprehensive energy policy to sustain economic growth in the long-term. (C) 2013 Elsevier Ltd. All rights reserved.