Simultaneous consideration of spatial heterogeneity and spatial autocorrelation in European innovation: a spatial econometric approach based on the MGWR-SAR estimation

The paper focuses on a simultaneous consideration of both spatial heterogeneity and spatial autocorrelation in the context of European regional innovation activities. A new class of data generating processes, the Mixed Geographically Weighted Regression-Spatial Autoregressive model, is the main instrument of the analysis. We deal with 220 European regions, and the components of the Regional Innovation Scoreboard 2019 are the basis of the analysis. Patent Cooperation Treaty applications are used as a measure of innovation output, and Scientific publications among the top-10% most cited publications worldwide, Research & Development expenditure in the business sector, Small and Medium-Sized Enterprises introducing product or process innovations and Human resources in science and technology are included as innovation inputs. The main research hypothesis is that there are spatial innovation spillovers among the European regions. Changes in innovation inputs in a specific region affect the patent applications not only in this region but these changes might also significantly impact neighbouring regions. At the same time, we assume that the effects of changes in innovation inputs differ across regions, mainly between regions belonging to the top innovators and lagging regions. The results indicate that a spatial differentiation of the model parameters and spatial spillovers matter for innovation output. We detect significant differences between advanced and lagging regions. Therefore, heterogeneous responses to regional policy measures should be considered, and it is necessary to apply a more individual approach to the regional development of innovation activities.

Automated summary

The study focuses on the spatial heterogeneity and spatial autocorrelation in European regional innovation activities. The findings show significant differences between advanced and lagging regions, suggesting a need for a more individual approach to regional innovation development. The research also highlights the importance of spatial differentiation in model parameters and spatial spillovers for innovation output.