Beyond Parametric Bounds: Exploring Regional Unemployment Patterns Using Semiparametric Spatial Autoregression

Abstract

Background: It is a well-known phenomenon that nonlinearities that are inherent in the relationship among economic variables negatively affect the commonly used estimators in the econometric models. The nonlinearities cause an instability of the estimated parameters that, in particular, are unable to capture a local relationship between the response and the covariate. Objectives: The main aim of the paper is the simultaneous consideration of spatial effects as well as nonlinearities through an advanced semiparametric spatial autoregressive econometric model. The paper seeks to contribute to empirical studies of regional science focused on the application of semiparametric spatial autoregressive econometric models. Methods/Approach: We outline an approach that can be used to correct nonlinearities by incorporating a semiparametric idea within the framework of econometric models. We use an expansion by penalised basis splines that are highly flexible and are able to capture local nonlinearities between variables. Results: In the empirical study, we fit different econometric models that attempt to explain the dynamics of the European Union's regional unemployment. Conclusions: The results show that regional unemployment exhibits significant spatial dependence, indicating interconnectedness among neighbouring regions and suggesting the adoption of a semiparametric spatial autoregressive model for improved modelling flexibility, surpassing traditional parametric approaches.