The Summary Innovation Index (SII) is a tool used by the European Commission to assess the innovativeness of European Union member states. The aim of the SII is to monitor progress in innovation and support innovation policies within the EU.
The key features of the Summary Innovation Index are as follows:
Multidimensionality: The SII considers various aspects of innovativeness. It assesses factors such as research and development expenditures, human resources in science and technology, innovative activities in the business sector, venture capital investments, intersectoral collaboration, and the innovativeness of small and medium-sized enterprises.
Comparability: The index enables the comparison of innovativeness outcomes among EU member states. It serves as an important tool for the European Commission to identify best practices and areas that require further development.
Timeliness of data: The SII utilizes the latest available statistical data, including data from Eurostat, survey research, scientific reports, and other sources, to reflect the actual state of innovativeness in member states.
Indicator-based approach: The SII comprises several indicators of innovativeness, which are aggregated to obtain an overall score. These indicators include research and development expenditures, scientific publications, patents, innovation in businesses, access to innovation financing, and scientific-industrial collaboration.
Overall, the Summary Innovation Index serves as a valuable tool for monitoring innovativeness progress at the EU level and supporting the identification of areas that require policy support and investment in research and development. It plays a crucial role in promoting competitiveness and sustainable development within Europe.
Step 1: Setting reference years
For each indicator, a reference year is identified for all countries based on data availability for all those countries for which data availability is at least 75%. For most indicators, this reference year lags one or two years behind the year in which the EIS is published.
Step 2: Imputing for missing values
Reference year data are then used for “2022”, etc. If data for a year-in-between are not available, missing values are replaced with the value for the previous year. If data are not available at the beginning of the time series, missing values are replaced with the next available year. The following examples clarify this step and show how ‘missing’ data are imputed. If data are missing for all years, no data will be imputed (the indicator will not contribute to the Summary Innovation Index).
Step 3: Identifying and replacing outliers
Chauvenet’s Criterion in statistical theory is used to determine outliers. Positive outliers are identified as those country scores which are higher than the mean across all countries plus twice the standard deviation. Negative outliers are identified as those country scores which are smaller than the mean across all countries minus twice the standard deviation. These outliers are replaced by the respective maximum and minimum values observed over all the years and all countries excluding the identified outliers. Table 5 summarises the outliers per indicator and year (negative outliers are shown in italics) for the full time series including imputed values. Years refer to the years for which raw data are available.
Table 5: Data availability by indicator
|Overview of positive and negative outliers||Positive / Negative outlier|
|1.1.1 New doctorate graduates in STEM||SI: 2013, 2016; CH: 2014-2020; UK 2018-2020|
|1.1.2 Percentage population aged 25-34 having completed tertiary education||LU: 2014-2021; RO: 2014-2021|
|1.1.3 Population aged 25-64 participating in lifelong learning||FI: 2014-2021; SE: 2014-2021|
|Attractive research systems|
|1.2.1 International scientific co-publications per million population||DK: 2019-2021; IS: 2016-2021; CH: 2014-2021|
|1.2.2 Top 10% most cited publications|
|1.2.3 Foreign doctorate students||LU: 2013-2020; CH: 2018-2020|
|1.3.1 Broadband penetration||DK: 2014-2021|
|1.3.2 Individuals who have above basic overall digital skills||NL: 2014-2021|
|Finance and support|
|2.1.1 R&D expenditure in the public sector||DK: 2013, 2015, 2018-2020|
|2.1.2 Venture capital expenditures||EE: 2021; CY: 2019-2021; LU: 2016; MT: 2017-2019; UK: 2021|
|2.1.3 Direct government funding and government tax support for business R&D||IE: 2014; FR: 20212-2019; HU: 2015; AT: 2012; SI: 2012-2013; UK: 2017-2019|
|2.2.1 R&D expenditure in the business sector||IL: 2013-2020|
|2.2.2 Non-R&D innovation expenditures||RS: 2016-2020; TR: 2013-2017|
|2.2.3 Innovation expenditure per person employed||BE: 2016-2018; DE: 2014-2018; SE: 2011-2018|
|Use of information technologies|
|2.3.1 Enterprises providing training to develop or upgrade ICT skills of their personnel||FI: 2013, 2014; IS: 2013-2019; RO: 2017|
|2.3.2 ICT specialists||SE: 2014-2021; IL: 2021; TR: 2014-2021|
|3.1.1 SMEs introducing product innovations||EE: 2018, 2019; EL: 2020; CY: 2018, 2019; RO 2013-2017|
|3.1.2 SMEs introducing business process innovations||BE: 2020; E: 2020; CY: 2019-2020; RO: 2013-2020|
|3.1.3 SMEs innovating in-house|
(years shown refer to year of CIS survey)
|3.2.1 Innovative SMEs collaborating with others||BE: 2013-2015; EE: 2018, 2019; CY: 2018-2020; FI: 2020; NO: 2018-2020; UK: 2016, 2017|
|3.2.2 Public-private co-publications||DK: 2020, 2021; IS: 2016-2021; CH: 2015-2021|
|3.2.3 Job-to-job mobility of Human Resources in Science & Technology||RO: 2019, 2020|
|3.3.1 PCT patent applications||FI: 2011-2014; SE: 2011-2018; IL: 2011-2018|
|3.3.2 Trademark applications||CY: 2015-2021; LU: 2014-2017; MT: 2014-2021|
|3.3.3 Design applications||BG: 2014, 2015; LU: 2014-2016; MT: 2014-2018|
|4.1.1 Employment in knowledge-intensive activities||LU: 2014-2021; IL: 2014-2021|
|4.1.2 Employment in innovative enterprises||RO: 2014-2021|
|4.2.1 Medium and high technology product exports||AL: 2014-2021; IS: 2014-2021; NO: 2018|
|4.2.2 Knowledge-intensive services exports|
|4.2.3 Sales of new-to-market and new-to-enterprise innovations||IE: 2020; EL: 2018, 2019; AL: 2013-2020|
|4.3.1 Resource productivity||NL: 2017-2020; CH: 2015-2020; UK: 2019, 2020|
|4.3.2 Air emissions by fine particulates (PM2.5) in Industry||MT: 2019; EE: 2013, 2015, 2017; LV: 2012-2019; PT: 2012-2019; RS: 2017-2019|
|4.3.3 Development of environment-related technologies||BG: 2015; DK: 2012, 2017-2019; EE: 2012; MT: 2016, 2017; AL: 2013, 2016-2019; BA: 2012, 2013, 2018, 2019; MK: 2014, 2017|
Step 4: Transforming data that have highly skewed distributions across countries
Most of the indicators are fractional indicators with values between 0% and 100%. Some indicators are unbound indicators, where values are not limited to an upper threshold. These indicators can be highly volatile and can have skewed data distributions (where most countries show low performance levels, and a few countries show exceptionally high levels of performance). For these indicators where the degree of skewness across the full eight-year period is above one, data have been transformed using a square root transformation, i.e. using the square root of the indicator value instead of the original value. For the following indicators data have been transformed: Venture capital expenditures, Non-R&D innovation expenditures, PCT patent applications, Trademark applications, and Air emissions by fine particulates (PM2.5) in industry (Table 6).
Table 6: Skewness of the indicators before and after a possible data transformation
|Innovation dimension / Indicator||Skewness||Skewness after trans-formation|
|1.1.1 New doctorate graduates in STEM||0.415|
|1.1.2 Population aged 25-34 having completed tertiary education||0.005|
|1.1.3 Population aged 25-64 participating in lifelong learning||0.579|
|Attractive research systems|
|1.2.1 International scientific co-publications per million population||0.690|
|1.2.2 Top 10% most cited publications||0.104|
|1.2.3 Foreign doctorate students||0.714|
|1.3.1 Broadband penetration||0.165|
|1.3.2 Individuals who have above basic overall digital skills||-0.003|
|Finance and support|
|2.1.1 R&D expenditure in the public sector||0.187|
|2.1.2 Venture capital expenditures||1.143||0.286|
|2.1.3 Direct government funding and government tax support for business R&D||0.840|
|2.2.1 R&D expenditure in the business sector||0.633|
|2.2.2 Non-R&D innovation expenditures||1.451||0.374|
|2.2.3 Innovation expenditure per person employed||0.627|
|Use of information technologies|
|2.3.1 Enterprises providing training to develop or upgrade ICT skills of their personnel||0.103|
|2.3.2 ICT specialists||0.330|
|3.1.1 SMEs introducing product innovations||-0.179|
|3.1.2 SMEs introducing business process innovations||-0.289|
|3.1.3 SMEs innovating in-house||not classified|
|3.2.1 Innovative SMEs collaborating with others||0.713|
|3.2.2 Public-private co-publications||0.977|
|3.2.3 Job-to-job mobility of Human Resources in Science & Technology||0.013|
|3.3.1 PCT patent applications||1.058||0.567|
|3.3.2 Trademark applications||1.664||0.533|
|3.3.3 Design applications||0.563|
|4.1.1 Employment in knowledge-intensive activities||0.206|
|4.1.2 Employment in innovative enterprises||-0.275|
|4.2.1 Medium and high technology product exports||-0.598|
|4.2.2 Knowledge-intensive services export||0.090|
|4.2.3 Sales of new-to-market and new-to-enterprise innovations||0.431|
|4.3.1 Resource productivity||0.780|
|4.3.2 Air emissions by fine particulates (PM2.5) in Industry||1.651||0.974|
|4.3.3 Development of environment-related technologies||0.532|
Step 5: Determining Maximum and Minimum scores
The Maximum score is the highest score found for the eight-year period within all countries excluding positive outliers. Similarly, the Minimum score is the lowest score found for the eight-year period within all countries excluding negative outliers.
Step 6: Calculating re-scaled scores
Re-scaled scores of the country scores (after correcting for outliers and a possible transformation of the data) for all years are calculated by first subtracting the Minimum score and then dividing by the difference between the Maximum and Minimum score. The maximum re-scaled score is thus equal to 1, and the minimum re-scaled score is equal to 0. For positive and negative outliers, the re-scaled score is equal to 1 or 0, respectively.
Step 7: Calculating composite innovation indexes
For each year, a composite Summary Innovation Index is calculated as the unweighted average of the re-scaled scores for all indicators where all indicators receive the same weight (1/32 if data are available for all 32 indicators).
Step 8: Calculating relative-to-EU performance scores
Performance scores relative to the EU are then calculated as the SII of the respective country divided by the SII of the EU multiplied by 100. Relative performance scores are calculated for the full eight-year period compared to the performance of the EU in 2015 and for the latest year also to that of the EU in 2022. For the definition of the performance groups, only the performance scores relative to the EU in 2022 have been used.