Testing for country heterogeneity in growth models using a finite mixture approach

We define a bivariate mixture model to test whether economic growth can be considered exogenous in the Solovian sense. For this purpose, the multivariate mixture approach proposed by Alfo and Trovato is applied to the Bernanke and Gurkaynak extension of the Solow model. We find that the explanatory power of the Solow growth model is enhanced, since growth rates are not statistically significantly associated with investment rates, when cross-country heterogeneity is considered. Moreover, no sign of convergence to a single equilibrium is found. Copyright (C) 2008 John Wiley & Sons, Ltd.