USING ARTIFICIAL NEURAL NETWORKS FOR INCOME CONVERGENCE

Economic convergence is an important topic in modern Macroeconomics. Economic convergence refers to the tendency of per capita income of countries (regions) to approach their steady-state value. Two types of convergence are identified in the literature: Conditional and Absolute Convergence. This paper studies income convergence between 177 world countries during the period of 1980-2006 by using the neoclassical growth model of Barro-Sala-i-Martin for both kinds of convergence. Non-linearity of the underlying relationships, the restrictiveness of assumptions of functional forms and econometric problems in the estimation and application of theoretical models, advocate for the use of Artificial Neural Networks (ANN) algorithms. We show that by changing the quantitative tools of analysis and using ANN results become more precise. Results show that absolute convergence does not exist and conditional convergence is insignificant