This paper applies multidimensional clustering of EU-28 regions to identify similar specialisation strategies and socioeconomic characteristics. It builds on an original dataset where the EU-28 regions are classified according to their socioeconomic and demographic features and to the strategic priorities outlined in their research and innovation smart specialisations strategy (RIS3). The socioeconomic and demographic classification associates each region to one categorical variable (with 19 modalities), while the classification of the RIS3 priorities clustering was performed separately on “descriptions” (21 Boolean categories) and “codes” (11 Boolean Categories) of regions’ RIS3. Three techniques of clustering have been applied: Infomap multilayer algorithm, Correspondence Analysis plus Cluster Analysis and cross tabulation. The most effective clustering, in terms of both the characteristics of the data and the emerging results, is that obtained on the results of the Correspondence Analysis. By contrast, due to the very dense network induced by the data characteristics, the Infomap algorithm does not produce significant results. Finally, cross tabulation is the most detailed tool to identify groups of regions with similar characteristics. In particular, in the paper we present an application of cross tabulation to focus on the regions investing in sustainable development priorities. Policy implications of methods implemented in this paper are discussed as a contribution to the current debate on post-2020 European Cohesion Policy, which aims at orienting public policies toward the reduction of regional disparities and the enhancement of complementarities and synergies within macroregions.

Russo, M., P., Pavone, F., Pagliacci, S., Righi e A., Giorgi. "Detecting multidimensional clustering across EU regions. Focus on R&I smart specialisation strategies and on socio-economic and demographic conditions" Working paper, DEMB WORKING PAPER SERIES, Dipartimento di Economia Marco Biagi - Università di Modena e Reggio Emilia, 2019. https://doi.org/10.25431/11380_1196153

I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Powered by IRIS-about IRIS-Utilizzo dei cookie

 Copyright © 2022