Cointegration analysis for cross-sectionally dependent panels: The case of regional production functions

This paper employs recently developed non-stationary panel methodologies that assume cross-section dependence to estimate a production function for Italian regions over the 1970-2003 period. The analysis consists of three steps. First, unit root tests for cross-sectionally dependent panels are applied. Second, the existence of a cointegrating relationship among value added, physical capital and human capital-augmented labour is investigated, fully allowing for cross-section dependence. Then, the appropriate Fully Modified Ordinary Least Square estimators developed by Bai and Kao [Bai, J., Kao, C. 2006. On the Estimation and Inference of a Panel Cointegration Model with Cross-Sectional Dependence. In: B.H. Baltagi (Ed) Panel Data Econometrics: Theoretical Contributions and Empirical Applications, Elsevier Science: Amsterdam; 2006, pp.3-30.] are used to estimate the long-run relationship. We find that neglecting cross-section dependence can have a strong impact on the estimated long-run input elasticities, generally imparting them an upward bias.