The aim of this work is to analyze the relationship between inequality and economic growth. The results obtained by previous empirical papers were mixed. Authors such as Persson and Tabellini (1991) or Alesina and Rodrik (1994), in fact, find evidence of a negative relationship between the two variables of interest; on the contrary, Li and Zou (1998) and Forbes (2000) find that greater inequality is associated with faster economic growth. Barro (2000 and 2008) claims that inequality has a positive effect on GDP growth in advanced economies, but has a negative impact in developing ones. The present work considers two samples of OCSE countries; in the full sample 33 countries are analyzed for the 1971-2010 period and inequality data are taken from the UNU-WIDER dataset. In the restricted sample 27 countries are considered for the 1981-2010 period and inequality data from the Luxembourg Income Study are used. The estimation technique employed are fixed effects, random effects and GMM Arellano-Bond. The Gini coefficient has been used as inequality measure and ten-years averages of the data have been computed in order to reduce the problem linked to the limited variability of the Gini coefficient across time. In the case of the fixed effects and the GMM estimates on the full sample, positive and statistically significant estimated coefficients for the inequality measure are obtained. The value ranges from 1.2 to 1.5; this means that a 1% increase in inequality within a country would be followed by a more than proportional increase in the rate of economic growth in the following ten years. All the other estimated coefficients, when statistically significant, take the expected sign and the Sargan test confirms that the over-identifying restriction used for the GMM estimation are valid. However, there is room for further research, in particular by considering that: the relationship between the two variables of interest may be quadratic and not linear, the time horizon considered may significatively influence the estimation results and finally it would be necessary to extend the sample by also including developing countries (non-OCSE members).