GROWTH, CONVERGENCE AND PUBLIC INVESTMENT. A BAYESIAN MODEL AVERAGING APPROACH

The aim of this paper is twofold. Firstly, we study the determinants of growth among a wide set of potential variables for the Spanish provinces (NUTS3). We include several types of private, public and human capital in the group of growth factors. Moreover, we analyse whether Spanish provinces have converged in economic terms in the past decades. The second objective is to overcome the problems of model uncertainty and robustness of estimated parameters in growth regressions using cross-section and panel data techniques. For this purpose, we use a Bayesian Model Averaging (BMA) approach. The Bayesian methodology constructs parameter estimates as a weighted average of linear regression estimates for every possible combination of included variables. The weight of each regression estimates is given by the posterior probability of each model. This technique allows us to obtain parameter estimates that are robust to model specification.