Résumé : The aim of this paper is to empirically examine the relationship between saving and investment for 6 Middle East and North African Countries for the period 1980-2008. To this end, we use panel cointegration analysis and Error Correction Model techniques. The long run estimation reveals causality between investment and saving for the entire sample. The Granger causality tests confirm this result and validate the presence of bidirectional causal relationship between investment and saving. However, the short run estimation shows no causality between the two variables for the entire sample. At the individual level, saving Granger cause investment for Bahrain and Saudi Arabia only.