The Standard of Living of Inhabitants and the Scientific and Technological Potential in Selected European Union Regions
Purpose: This paper aims to determine the relationship between the standard of living of the inhabitants of selected regions of the European Union and the scientific and technological potential. Design/Methodology/Approach: The study covered 60 regions – NUTS 2 – in 13 European Union Member States. The data concerned the year 2018. Due to the multidimensional character of the analyzed categories, a canonical analysis was used as a generalization of multiple linear regression into two sets of variables. In order to evaluate the statistical significance of the analyzed canonical variables, the Wilks' lambda significance test was conducted. As part of the canonical analysis, canonical correlations, total redundancy, and extracted variances were calculated. Findings: Based on results of the classical correlation analysis, it can be concluded that there is a positive, high, and statistically significant correlation dependence (Spearman's rank correlation coefficient was nearly 0.66) between the standard of living of inhabitants from selected EU regions and S&T potential (measured by synthetic measures constructed based on the TOPSIS method). Five statistically significant canonical variables (components) were identified in the canonical analysis. The value of the largest and most statistically significant canonical correlation was over 0.97. For the last (fifth) statistically significant canonical variable, this value was over 0.72. Practical Implications: The results of the conducted research (among others ranking of countries according to the standard of living of the inhabitants) may be indirectly used by the central and local authorities responsible for local and regional development (including undertaking pro-social and pro-innovation activities) in the context of the choice of the direction for the socio-economic restructuring of particular countries and local government units. Originality/Value: A rarely used multivariate in socio-economic research, canonical analysis is a valuable tool for assessing the relationships between two compiled, multi-faceted categories.