Local versus regime convergence regression models: a comparison of two approaches

摘要: Two types of econometric models have typically been used in geographical research: global and local. The former produces parameter estimates that represent an average type economic behavior; is, for each variable there is one regression coefficient the entire sample. latter suggests relationship interest can vary widely over space allowing parameters to change across spatial entities. Commonly, results obtained from these two different approaches are compared other determine which model performed better. aim this paper twofold. First foremost, it show a comparison between local problematic misleading since overlooks critical group known as regime models. This means should be extended by including all (i.e. global, regime). Sometimes, perform well as, or even better, than (more complex) something taken into account empirical studies. Secondly, investigates convergence process regions (enlarged) European Union (EU) period 1995–2005. (convergence) seems better any employed, implying very low rate among highlighting heterogeneous impact EU integration process.