THE RIS UNDER SCRUTINY

METHODOLOGICAL DEBATE ON THE ‘REGIONAL INNOVATION SCOREBOARD’.

METHODOLOGICAL DEBATE ON THE ‘REGIONAL INNOVATION SCOREBOARD’.

From the point of view of any one region, we can therefore divide all the regions of Europe according to the significance of the differences in their RIS. The first group includes regions with a significantly higher RIS; secondly, those with a significantly lower RIS; and, finally, those that do not differ significantly from the region in question. For example, we can state that, in the case of Aragon, the first group is made up of the Basque Country, Navarre, Madrid Region, Catalonia, and Valencia Region. The second group includes Asturias, Cantabria, Castile-La Mancha, Extremadura, the Balearic Islands, Andalusia, and the Canary Islands. Finally, the third group includes Galicia, La Rioja, Cas- tile-León, and Murcia.

Tables 5, 6 and 7 show the group of European regions that have a RIS that is significantly higher, lower and equal to that of a specific region, taking the Basque Country as an exam- ple. The Basque Country is chosen to illustrate the methodological approach proposed in this study to obtain a robust ranking of regions, as it is the Spanish region that is best positioned in the European context. Of the 225 regions included in this study, only 45 are significantly higher the Basque Country (see Table 5), while 83 are significantly lower (Table 6). This im - plies that the other 97 European regions (see Table 7) do not differ significantly from the Basque Country if we take the critical value of 95% confidence. It is worth noting that, from a statistical point of view, Catalonia, Navarre, Madrid Region and Valencia Region do not show significant differences from the Basque Country in terms of variations in the weights of the RIS synthetic index. (TABLE 5) (TABLE 6) (TABLE 7)

˜ TABLE 4

Comparison of RIS between Spanish regions, assuming random weights (likelihoods) 7

Source: Drafted in-house based on European Union (2021b)

LIKELIHOOD OF HAVING A LOWER RIS THAN

1 2 3 4 5 6 7 8 9 1011121314151617

1 2 3 4 5 6 7 8 9

Andalusia Aragon Asturias

- 0.00 0.10 0.55 1.00 0.04 0.87 0.01 0.00 0.93 0.00 0.00 0.00 0.01 0.00 0.00 0.00

1.00 - 0.96 0.97 1.00 0.98 1.00 0.86 0.00 1.00 0.79 0.54 0.00 0.79 0.00 0.00 0.02

0.90 0.04 - 0.80 1.00 0.51 0.96 0.24 0.00 0.97 0.06 0.18 0.00 0.38 0.00 0.00 0.00

0.45 0.03 0.21 - 1.00 0.18 0.75 0.11 0.00 0.80 0.05 0.00 0.00 0.01 0.00 0.00 0.00

0.00 0.00 0.00 0.00 - 0.00 0.00 0.00 0.00 0.02 0.00 0.00 0.00 0.00 0.00 0.00 0.00

0.96 0.02 0.50 0.82 1.00 - 0.99 0.23 0.00 0.97 0.04 0.12 0.00 0.32 0.00 0.00 0.00

0.14 0.00 0.05 0.25 1.00 0.01 - 0.01 0.00 0.76 0.00 0.00 0.00 0.00 0.00 0.00 0.00

0.99 0.14 0.76 0.89 1.00 0.77 0.99 - 0.00 1.00 0.27 0.32 0.00 0.57 0.00 0.00 0.01

1.00 1.00 1.00 1.00 1.00 1.00 1.00 1.00 - 1.00 1.00 1.00 0.39 1.00 0.57 0.21 0.92

0.08 0.00 0.03 0.20 0.98 0.03 0.25 0.00 0.00 - 0.00 0.00 0.00 0.00 0.00 0.00 0.00

1.00 0.22 0.94 0.96 1.00 0.96 1.00 0.73 0.00 1.00 - 0.43 0.00 0.70 0.00 0.00 0.00

1.00 0.45 0.82 1.00 1.00 0.88 1.00 0.67 0.00 1.00 0.57 - 0.01 0.98 0.01 0.01 0.00

1.00 1.00 1.00 1.00 1.00 1.00 1.00 1.00 0.61 1.00 1.00 0.99 - 1.00 0.62 0.32 0.87

0.99 0.19 0.62 0.99 1.00 0.67 1.00 0.42 0.00 1.00 0.30 0.03 0.00 - 0.00 0.00 0.00

1.00 1.00 1.00 1.00 1.00 1.00 1.00 1.00 0.43 1.00 1.00 0.99 0.37 1.00 - 0.09 0.84

1.00 1.00 1.00 1.00 1.00 1.00 1.00 1.00 0.80 1.00 1.00 0.99 0.66 1.00 0.91 - 0.91

1.00 0.98 1.00 1.00 1.00 1.00 1.00 0.99 0.08 1.00 1.00 1.00 0.13 1.00 0.16 0.09 -

Balearic Islands Canary Islands

Cantabria

Castile-La Mancha

Castile-León

Catalonia

10 11 12 13 14 15 16 17

Extremadura

Galicia La Rioja

Madrid Region Murcia Region

Navarre

Basque Country Valencia Region

˜ TABLE 5

Comparison of a region with the rest of the European re- gions with a significantly greater RIS Source: Drafted in-house based on European Union (2021b)

work provides an accurate measurement of the likelihood of there being a weighting that allows one region to overtake another, assum- ing that the Commission’s weighting placed it in a lower-ranked position. The bootstrap technique followed in this analysis allows us to obtain this likelihood for each pair of regions included in the RIS with a significance level of 95%. Table 4 shows just the results for the Spanish Regions. A colour scale has been added to make the chart easier to read, indicating whether likelihood is moving away from the unit (green) or towards it (red). (TABLE 4)

gions. For example, taking the critical value of 95%, in column seven of Table 4, we could infer that La Rioja (12) has a significantly lower RIS than the Basque Country (16 - with a likelihood of 99%), Navarre (15 - likelihood of 99%), Ma - drid Region (13 - likelihood of 99%), Catalonia (9 - likelihood of 100%), and Valencia Region (17 - likelihood of 100%). Similarly, we can study the likelihood of a certain region having a higher RIS than another European region, tak- ing the critical value of 5%. Column 5 in Table 4 shows that the Basque Country (16) has a higher RIS than all the Spanish regions except Navarre (15, which would have a 9% likelihood of having a higher ranking), Madrid (13, 32% likelihood), Catalonia (9, 21% likelihood) and Valencia (17, 9% likelihood), for which the likeli - hood is higher than 5%.

REGIONS WITH SIGNIFICANTLY HIGHER RIS THAN THE BASQUE COUNTRY

BE1 BE2

Région de Bruxelles-Capitale

DEA2 Köln DEB3 Rheinhessen-Pfalz IE06 Eastern and Midland ES21 Basque Country FR1 Île de France NL22 Gelderland NL31 Utrecht NL32 Noord-Holland NL33 Zuid-Holland NL41 Noord-Brabant NL42 Limburg AT1 Ostösterreich AT2 Südösterreich AT3 Westösterreich FI1B Helsinki-Uusimaa

FI1C FI19 FI1D SE11 SE12 SE22 SE23 SE33

Etelä-Suomi Länsi-Suomi

Vlaams Gewest

DK01 Hovedstaden DK04 Midtjylland

Pohjois- ja Itä-Suomi

Stockholm

DE11 Stuttgart DE12 Karlsruhe DE13 Freiburg DE14 Tübingen

Östra Mellansverige

Sydsverige Västsverige

Övre Norrland NO01 Oslo og Akershus

DE21 Oberbayern DE25 Mittelfranken DE3 Berlin DE6 Hamburg DE71 Darmstadt DE72 Gießen DE91 Braunschweig

NO05 Vestlandet NO06 Trøndelag UKH

East of England

These likelihoods provide a measurement of the significance of the differences between re -

UKI UKJ UKK

London

South East South West

7 Given the number of regions considered (225), it is not possible to represent a table equivalent to Table 4 for all European regions, although the authors can provide this information upon request.

42

43

Made with FlippingBook - Online Brochure Maker