Knowledge Space Relatedness and Complexity A Regional Analysis in Turkey
Yildiz Social Science Review 2021, Vol. 7, Issue 2, pp. 110-122; doi.org/10.51803/yssr.869824
Abstract
Keywords: Branching; relatedness density; knowledge space; regional diversifi-cation; regional development; smart specialization; patents; Turkey; JEL Classification: R10; R11 R58
1. Introduction
Unlike the “one size fits all” approach to regional development, it is well known that enabling each region to have a distinct focus on its unique characteristics is key to sustainable competitive advantage (European Commission, 2020a). In 2011, Smart Specialisation Strategy was identified as the main programme by the European Union for reaching its smart, sustainable, and inclusive growth objectives. It has also been described as a supporting tool for its Territorial Cohesion Policy which is essential for eliminating differences between regions by ensuring a balanced development. It is defined as an innovative perspective based on integrated and place-based economic transformation by focusing on each region’s strengths, competitive advantages, and potential for excellence (Foray et al., 2012). The role of conducting placebased innovation strategies also comes to the forefront in creating clusters for high-value added and innovative investments that require high amount of cumulative knowledge (Widuto, 2019). Smart innovation strategies make it possible to create interregional clusters by linking regions with similar knowledge and enable the accumulation of knowledge required for progress. Therefore, the focus on regional specialization policies should be on region’s competencies where each region discovers its own growth path. Potential economic activities of a region should be determined by taking into account the relatedness of the industries in the region (the extent to which a new technology/occupation/industry is related to pre-existing skills and capabilities in the region) and technological complexity of the industries (potential socio-economic impact of diversifying into specific activities) (Hidalgo and Hausmann, 2009; Hidalgo et al., 2018; Balland et al., 2019). This concept
is fundamental in smart specialization policies. Balland et al., (2019) propose that regions should develop on sectors that are technologically related to the regions’ core strengths and are difficult to replicate outside the region. Relatedness and complexity are two key dimensions in choosing sectors for regional smart specialization. In Turkey, early studies with a distinct focus on regional specialization are on cluster formation in Turkey (see, Çelik et al., 2019 for a review). The studies demonstrate geographical distribution of economic activity. There are also studies with special focus on technological composition of clusters. Kaygalak (2013) propose that none of the identified clusters include high-tech sectors. Kaygalak and Reid (2016) and Gezici et al., (2017) further demonstrate that increases in sectoral agglomerations tend to be within the medium-low and medium-high technology sectors. In general, existing studies confirm that Turkey’s industrial activities contain medium and low technologies. In relation to the diversity of economic activities and knowledge bases and, indicators of regions’ core strengths, Kuştepeli et al., (2013) explore the impact of related variety on economic performance of the regions. Following the regional innovation policy model, based on the idea of constructing regional advantage (Asheim et al., 2011), Gülcan et al., (2011) demonstrate differentiated knowledge bases in Turkish textile industry. Although existing studies in Turkey reveal evidence on differences in spatial distribution, technology composition and knowledge of economic activities, little is known on how different technology classes are connected to each other as well as how relatedness and knowledge complexity of the regions have impact on regional innovativeness. Relatedness shows potential for regions’ branching opportuni-
Yıldız Social Science Review, Vol. 7, No. 2, pp. 110–122, 2021
ties into new and related technologies. Related technologies could be source of creating and developing innovations. Similarly, complexity of knowledge indicates that regional capabilities are unique and hard to imitate in other regions, thus creating source of regional competitiveness. Building upon the smart and inclusive growth priorities defined by the EU, the paper focuses on the role of knowledge for strengthening innovation in individual regions. Knowledge-based economy dimension of the Smart Specialization framework can be regarded as an approach that will help regions to identify and develop their own competitive advantages, and as a result boost growth and jobs across regions (European Commission, 2020b). Thus, this paper aims to contribute designing policies for regional development based on regions’ local competitive assets and own competitive advantages by tracing undiscovered opportunities within regions. There are three aims of the paper: The first aim is to map relatedness between technology classes in Turkey for 2010 and 2017. The second aim is to understand relatedness (branching opportunities) and knowledge complexity in Turkey’s regions for 2010 and 2017. The third aim is to demonstrate how relatedness and knowledge complexity are related to regions’ innovativeness. The paper proceeds as follows. In section 2, theoretical background of the regional diversification and economic complexity concepts is explained. In section 3, the data and analysis methods used in the study are presented. In section 4, findings on knowledge space, and relatedness and complexity estimations as well as the econometric analysis are shown. In section 5, a conclusion based on our findings is provided.
novative regions. The evolutionary discourse (Nelson and Winter, 1982; Frenken et al., 2007; Boschma and Frenken, 2006) focuses on evolutionary principles to explore how firms, industries, regions change over time. Regional growth is a dynamic process and path dependent (Kogler et al., 2013; Martin and Sunley, 2015). Central to sustainable long run growth is the influence of the capacity to produce economically valuable knowledge and innovativeness (Schumpeter, 1939; Nelson and Winter, 1982). However, it is also well documented and argued that distribution of knowledge is uneven across geographies thus causing differences in economic growth and development (Whittle and Kogler, 2019). Production of knowledge and innovativeness explain differences in economic performance of the regions (Schumpeter, 1942; Solow, 1956; Nelson and Winter, 1982; Romer, 1990). In their work on smart specialization, Balland et al., (2019) combine regional diversification literature (Hidalgo et.al., 2018; Neffke et al., 2011) and economic complexity literature (Hidalgo and Hausmann, 2009) and argue that relatedness and knowledge complexity are key concepts for a place-based policy (Boschma, 2014). Relatedness concept is related to the idea that knowledge creation is the combination of existing ideas. Foundations of knowledge and innovation are related to re-construction of the components of core ideas and therefore an evolutionary process. Frenken and Boschma (2007) propose that diversification of the economic activities is a branching process and the emergence of new technologies is not random and rather dependent on past knowledge. Innovations and new technologies are based on existing set of capabilities (Boschma, 2017). In addition to the significance of relatedness (as operationalized by relatedness density) for branching opportunities, regions tend to have competitive advantage when the technologies are unique and hard to copy. What is highly valuable for sustainable regional growth is the ability to create knowledge that tends to be complex. Knowledge complexity resulting from valuable and tacit knowledge is difficult to imitate and access by others (Hidalgo and Hausmann, 2009). Balland and Rigby (2017) demonstrate that complexity correlates with the long run patterns of economic performance and regions develop based on their existing knowledge cores. Following the regional diversification literature and economic complexity literature summarized above the paper aims to test the hypothesis that regional innovativeness is positively correlated with regions’ relatedness density and knowledge complexity. Relatedness proposes a relationship between specialization of a new activity and the presence of related activities in that location (Hidalgo et al., 2018). Similarly, complexity as measured by the presence of complex (hard to imitate) activities in the regions results with valuable economic outcomes coupled with tacit knowledge (Rigby et al., 2019; Maskell & Malmberg, 1999).
2. Theoretical Background
The theory is based on the view that regional competitive advantage depends on the conditions on the use of regions’ core knowledge and competencies. This idea has grounds on the stream of literature on regional innovation systems (Freeman, 1995; Cooke et al., 1997) and learning regions (Morgan, 1997; Lundvall and Johnson, 1994). The work on constructing regional advantage brings together the concepts like related variety, knowledge bases and policy platforms (Asheim et al., 2011). As suggested by Balland and Rigby (2017), geography has a significant role in determining the emergence and evolution of knowledge. The literature on regional accumulation of economic activities starts with the work of Marshall (1890) on agglomeration externalities. The central idea is that economic performance of regions is related to regional specialization and co-location of economic activities. Jacobs (1969) further proposed that different industries where there is variety of economic activities causes diversification externalities. Jacobian externalities cause knowledge spillovers between different industries and diversification leads to more in-
Yıldız Social Science Review, Vol. 7, No. 2, pp. 110–122, 2021
3.1. Data
To identify technological fields and compute measures of relatedness and knowledge complexity, we use OECD-REGPAT database January 2020 Edition (OECD, 2020). OECD-REGPAT contains patent data that are linked to the regions utilizing the addresses of the applicants and inventors. Regional patent data covers more than 5500 regions across OECD countries1. In this study, we use patent data for the years 2010 and 20172. The patent data is aggregated at NUTS3 level. The data is cleaned and grouped according to World Intellectual Property Organization (WIPO) technology classification “New concept of technology classification, update: May 2008” (Schmoch, 2008). According to May 2008 classification, IPC codes are grouped according to 5 technology classes and 35 sub-technology classes. We use the latest version (July 2019) of WIPO IPC-Technology Concordance Table to group IPC codes of the patents into WIPO technology classes.
3.2. Analysis Methods
3.2.1. Measuring Relatedness Relatedness is measured by the method following Boschma et al., (2015) and Rigby (2015). The method is based on counting the number of patent claims for a given period that contains a co-class pair of technologies i and j and standardizing this count by the total number of patents that contain i and j. Relatedness between technology i and j (φij) is a standardized measure of the frequency with which two IPC classes appear on the same patent. This paper follows the method outlined in Balland et al., (2019). The analysis is completed with EconGeo R package (Balland, 2017). Using relevant directions outlined in EconGeo R, we develop the knowledge space, which is a formal demonstration of relatedness between technologies. Relatedness across space is demonstrated by the knowledge structure of Turkey’s NUTS3 regions. Following the method demonstrated in Balland et al., (2019) and use of EconGeo R package, we calculate the density of technology production in the vicinity of individual technologies i for each NUTS3 region (r) in Turkey for 2010 and 2017. Relatedness of the regions is operationalized by relatedness density. As specified in Balland et al., (2019), the relatedness density of industry i, in region r at time t is presented below: (1) RDi,r,t is the relatedness density of technology i to all other technologies j where the region r has relative technological advantage (RTA) at time t. It is estimated by using the Equa1
tion (1). φij is technological relatedness of technology i with technology j. RTA is a binary variable that takes the value 1 when the region has higher share of patents in technology i in comparison to the share of patents in technology i in the country; and 0 otherwise (similar to the notion of location quotient). Relatedness density is therefore the technological relatedness of technology i to all other technologies j in which the region has relative technological advantage (RTA), divided by the sum of the technological relatedness of technology i to all other technologies in Turkey at time t. We use average relatedness density variable to measure regions’ potential for branching into new and related technologies. Average relatedness density of regions represents technological flexibility (the structure of the knowledge base) of the regions as demonstrated in Balland et al., (2015) with calculation procedures outlined in EconGeo Package (Balland, 2017). Average relatedness density (technological flexibility) represents the average relatedness of the technologies present in the region to all technological classes that are not yet in the city. Using average relatedness density variable, it is possible to reveal the branching opportunities and potential to diversify into new and related technologies in Turkey’s NUTS3 regions. 3.2.2. Measuring Complexity Quality of the knowledge created in the region is measured by complexity. Knowledge is valuable if it is difficult to replicate outside the geography. Knowledge that is tacit and sticky in the field is a source for competitive advantage in regions. This paper follows the method proposed by Hidalgo and Hausmann (2009) using export data. Balland et al., (2019) demonstrates the use of the method with patent data. The method connects the regions to technologies in which they have RTA. The complexity is determined by the range and ubiquity of the technologies that the regions use. The variable that measures complexity of knowledge in regions is knowledge complexity index (KCI). KCI has two components. Diversity is the number of technology classes in which the region (r) has relative technological advantage. Ubiquity is the number of regions that exhibit revealed technological advantage in a given technology (Balland and Rigby, 2017). Diversity and ubiquity are estimated with Equation (2) and Equation (3), respectively. (2) Where Mr,i is a binary variable that represents whether the region r has RTA in the production of technology i. (3) Where Mr,i is a binary variable that represents the number of regions with RTA in the production of technology i.
The database was produced by counting patent applications rather than an approval-based approach. Since it takes long time (generally two to ten years) for patents to be approved in some cases, it is possible that approval-based counts do not reflect the conjuncture at the relevant period. Therefore, the data consist of application-based patent counts, in line with the more common approach (Maraut et al., 2008). 2017 was the latest complete data available for Turkey in the REGPAT database during the time of data download.
Yıldız Social Science Review, Vol. 7, No. 2, pp. 110–122, 2021
The KCI combines the information obtained from the diversity and ubiquity variables following the iterations outlined in Hidalgo and Hausmann (2009). The method includes sequentially combining the diversity of regions and ubiquity of technological classes and simultaneously computes Equation (4) and Equation (5) over a series of n iterations:
the circles shows number of patents in each field and the colors indicate broad technology classes as demonstrated in Schmoch (2008). Comparison of two knowledge spaces demonstrates denser network ties among technologies in 2017 in contrast to 2010. Although chemistry has more patent applications in 2010, there is a visible decline in the number of patent applications in the chemistry field in 2017. In 2017, we see higher number of patent applications in electrical engineering where there are also stronger network ties across electrical engineering field with other technology fields, such as mechanical engineering, instruments and other fields.
3.2.3. Exploring Correlation of Relatedness Density and Complexity on Regional Innovativeness We use regression analysis to find the correlation of relatedness density and complexity with regions’ innovativeness. Innovativeness variable measures the number or patent applications in a region at time t (PAT). The independent variables in the model are, average relatedness density (ARD) and regions’ knowledge complexity index (KCI) for 2010 and 2017. In order to control for the impact of diversification of industries on patent applications, diversity variable (DIV) (measure of the number of technology classes in which the region has competitive advantage) is added. Data for the two time periods (2010 and 2017) is analyzed.
4.1. Turkey’s Knowledge Space (2010 and 2017)
Figure 1 demonstrates relatedness between technology fields in Turkey for the years 2010 and 2017. The size of
5. Conclusion
In this paper we examine the knowledge space, average relatedness density and knowledge complexity of the regions and their correlations with regional innovativeness as measured by number of patent applications in Turkey for two different years: 2010 and 2017. Our aim is to map out the technology space by exploring proximity between technology pairs as well as understanding spatial distribution of relatedness density and knowledge complexity of technologies and correlation with patent applications. The results can be summarized under two subheadings: Knowledge Space Investigation of the knowledge space, we see that network ties across individual technology classes became dens-
Table 8. Models with additional control variables Dependent variable: ln(PAT)
Clustered standard errors are shown in parentheses (); P-values are shown in square brackets [ ]; Coefficients are statistically *significant at the α≤0.1 level, **significant at the α≤0.05 level and *** significant at the α≤0.01 level.
Yıldız Social Science Review, Vol. 7, No. 2, pp. 110–122, 2021
er over time and higher number of patent applications are within the denser part of the knowledge space map. Knowledge space of 2010 and 2017 indicates a movement into new technologies, leaving of the old ones, possibly making a conclusion that it is possible to make projections for future technological paths in Turkey. The results reveal that the number of patents and intensity of technology connections changed between 2010 and 2017 away from chemistry to electrical engineering, a more complex technology class. In 2017, complexity index of fields in electrical engineering was high, particularly for audio-visual technology, telecommunications, digital communication, basic communication processes and IT methods for management. Patent Applications, Relatedness Density and Knowledge Complexity In Turkey, we see considerable heterogeneity across the cities in relation to patent applications, relatedness density and knowledge complexity. Regression results reveal that diversity and relatedness positively affect regional innovativeness as measured by patent applications. Knowledge space reveals that there is a shift of patents to more complex technologies. Findings propose that it is reasonable to support diversity and relatedness. The study is only a preliminary attempt to explore the distribution of knowledge across Turkey’s regions and its connection with innovativeness. First, it is not possible to reach to strong conclusions with only two years of observations, 2010 and 2017. Furthermore, the unit of spatial analysis of this study was 81 NUTS3 regions in Turkey, representing cities. Relatively smaller geographical areas might be a problem with moderately low frequency of patent applications where there is a threat of losing observations in econometric estimates. Further studies should redefine space where it would be possible to assemble the data according to Turkey’s 26 NUTS2 regions. Second, what further studies should consider is to add more years, and additionally work with three to five year windows to capture larger number of patent applications. The problem of this paper is that we only use 2 years of patent data. Since the number of patent applications varies from year to year, it is suggested that further studies include more years and work with aggregated data with time windows. Third, working with more years of patent data and grouping the data in time windows would likely to have significant implications for the knowledge space. In the current analysis, there is a considerable change in the knowledge space between 2010 and 2017. This difference between years may be due to the fact that in some technology classes there are hardly any patents or that some technologies may be present in one year and not available in the other year, which may make it difficult to observe the relatedness between technologies. This is also why there is a large fluctuation in KCI across the regions between the two years, where we do not expect such dramatic change in the complexity of
an economy between two years within a same decade. Another drawback of working with two years is that it restricts the possibility of working with time lags and our ability of testing the hypothesis that lagged values of ARD and DIV would have impact on the patent applications. We would expect that ARD and DIV will only have an effect with a time lag, and not having an influence on innovation in the same year. Additionally, due to low patenting activity at regional scale, when measuring ARD, further studies can include not only the technologies in which a region is specialized (with RTA >1), but also include those with lower RTAs, such as RTA>0.5. In summary, the results of the study should be interpreted with caveat due to limited number of observations. More data and aggregated time periods and regions are needed for further studies. Nevertheless, the paper reveals preliminary results that regional policies should focus on increasing diversity of industries and enabling conditions that potential new technologies in the region be close to the existing technological portfolio of the region. The paper supports the idea that smart specialization policy based on the relatedness framework is not a one size fits all policy and all regions ought to focus on their existing portfolios to draw new economic activities. Ethics: There are no ethical issues with the publication of this manuscript. Peer-review: Externally peer-reviewed. Authorship Contributions: Concept: S.A., M.A.; Design: S.A., M.A.; Supervision: S.A.; Resources – S.A., M.A.; Data collection and/or processing: S.A., M.A.; Analysis and/ or interpretation: S.A., M.A.; Literature search: S.A., M.A.; Writing Manuscript: S.A., M.A.; Critical review: S.A., M.A. Conflict of Interest: The author declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article. Financial Disclosure: The authors declared that this study has received no financial support.
References
- Asheim, B. T., Boschma, R., & Cooke, P. (2011). Constructing regional advantage: Platform policies based on related variety and differentiated knowledge bases. Regional studies, 45(7), 893-904. doi:10.1080/00343404.2010.543126
- Balland, P. A. (2017). Economic Geography in R: Introduction to the EconGeo Package. Papers in Evolutionary Economic Geography, 17(09), 1-75.
- Balland, P. A., & Rigby, D. (2017). The geography of complex knowledge. Economic Geography, 93(1), 1-23. doi:10.1080/00130095.2016.1205947
- Balland, P. A., Boschma, R., Crespo, J., & Rigby, D. (2019). Smart specialization policy in the European Union: relatedness, knowledge complexity and regional diversification. Regional Studies, 53(9), 1252-1268. doi:10.1080/00343404.2018.1437900
- Balland, P. A., Rigby, D., & Boschma, R. (2015). The technological resilience of US cities. Cambridge Journal of Regions, Economy and Society, 8(2), 167-184.
- Boschma, R. (2014). Constructing regional advantage and smart specialisation: Comparison of two European policy concepts. Italian Journal of Regional Science (Scienze Regionali), 13(1), 51-68.
- Boschma, R. A., & Frenken, K. (2006). Why is economic geography not an evolutionary science? Towards an evolutionary economic geography. Journal of economic geography, 6(3), 273-302.
- Çelik, N., Akgüngör, S., & Kumral, N. (2019). An assessment of the technology level and knowledge intensity of regions in Turkey. European Planning Studies, 27(5), 952-973. doi:10.1080/09654313.2019.1579301
- Cooke, P., Uranga, M. G., & Etxebarria, G. (1997). Regional innovation systems: Institutional and organisational dimensions. Research policy, 26(4-5), 475-491. doi:10.1016/S0048-7333(97)00025-5
- European Commission. (2020). Smart Specialization Platform. Retrieved from https://s3platform.jrc.ec.europa.eu/,
- Freeman, C. (1995). The ‘national system of innovation’ in historical perspective. Cambridge Journal of Economics, 19(1), 5-24.
- Frenken, K., & Boschma, R. A. (2007). A theoretical framework for evolutionary economic geography: Industrial dynamics and urban growth as a branching process. Journal of economic geography, 7(5), 635-649.
- Frenken, K., Van Oort, F., & Verburg, T. (2007). Related variety, unrelated variety and regional economic growth. Regional studies, 41(5), 685-697. doi:10.1080/00343400601120296
- Gezici, F., Yazgı-Walsh, B., & Kacar, S. (2017). Regional and structural analysis of the manufacturing industry in Turkey. Annals of Regional Science, 1(59), 209–230. doi:10.1007/s00168-017-0827-4
- Gülcan, Y., Akgüngör, S., & Kuştepeli, Y. (2011). Knowledge generation and innovativeness in Turkish textile industry: Comparison of Istanbul and Denizli. European Planning Studies, 19(7), 1229-1243. doi:10.1080/09654313.2011.573134
- Hidalgo, C. A., & Hausmann, R. (2009). The building blocks of economic complexity. Proceedings of the National Academy of Sciences, 106(26), 10570-10575.
- Hidalgo, C., Balland, P. A., Boschma, R., Delgado, M., Feldman, M., Frenken, K., . . . Zho, S. (2018). The principle of relatedness. In A. J. Morales, et al. (EDS), Unifying Themes in Complex Systems IX (pp. 451-457). Cham: Springer Nature.
- Jacobs, J. (1969). The Economy of Cities. New York: Vintage Books.
- James, G., Witten, D., Hastie, T., & Tibshirani, R. (2017). An Introduction to Statistical Learning with Applications in R (8 ed.). Springer Texts in Statistics.
- Kaygalak, İ. (2013). Türkiye sanayi coğrafyasında endüstriyel kümelenme ve bölgesel yoğunlaşma eğilimi. Beşeri Coğrafya Dergisi, 1(1), 67-81.
- Kaygalak, İ., & Reid, N. (2016). The geographical evolution of manufacturing and industrial policies in Turkey. Applied Geography, 70, 37-48. doi:10.1016/j.apgeog.2016.01.001
- Kuştepeli, Y., Gülcan, Y., & Akgüngör, S. (2013). The innovativeness of the Turkish textile industry within similar knowledge bases across different regional innovation systems. European Urban and Regional Studies, 20(2), 227-242.
- Lundvall, B. Ä., & Johnson, B. (1994). The learning economy. Journal of industry Studies, 1(2), 23-42. doi:10.1080/13662719400000002
- Marshall, A. (1890). Principles of Economics. 1 (First ed.). London: Macmillan.
- Martin, R., & Sunley, P. (2015). On the notion of regional economic resilience: conceptualization and explanation. Journal of Economic Geography, 15(1), 1-42.
- Maskell, P., & Malmberg, A. (1999). Localised learning and industrial competitiveness. Cambridge journal of economics, 23(2), 167-185.
- Morgan, K. (1997). The learning region: institutions, innovation and regional renewal. Regional Studies, 31(5), 491-503.
- Neffke, F., Henning, M., & Boschma, R. (2011). How do regions diversify over time? Industry relatedness and the development of new growth paths in regions. Economic geography, 87(3), 237-265.
- Nelson, R. R., & Winter., S. G. (1982). An evolutionary theory of economic change. Cambridge, Mass.: Harvard University Press.
- Rigby, D. L., Roesler, C., Kogler, D., Boschma, R., & Balland, P. A. (2019). Do EU regions benefit from smart specialization? Utrecht University Papers in Evolutionary Economic Geography, 19.
- Riveros, J. M. (2020, May 14). Ramsey RESET Test on Panel Data using Stata. Retrieved from M&S Research Hub.
- Romer, P. M. (1990). Endogenous technological change. Journal of political Economy, 98(5, Part 2), S71-S102.
- Schmoch, U. (2008). Concept of a technology classification for country comparisons. Final report to the world intellectual property organisation (WIPO). WIPO.
- Schumpeter, J. A. (1939). Business cycles: A theoretical, historical, and statistical analysis of the capitalist process (Vol. 1). New York and London: McGraw-Hill Book Company Inc.
- Schumpeter, J. A. (1942). Capitalism, Socialism and Democracy. New York: Harper & Row.
- Solow, R. M. (1956). A contribution to the theory of economic growth. The quarterly journal of economics, 70(1), 65-94.
- Whittle, A., & Kogler, D. F. (2019). Related to what? Reviewing the literature on technological relatedness: Where we are now and where can we go? Papers in Regional Science, 99(1), 97-113.
Share and Cite
AKGÜNGÖR, S.; ABAY, M. Knowledge Space Relatedness and Complexity A Regional Analysis in Turkey. Yildiz Social Science Review 2021, Vol. 7, pp. 110-122. https://doi.org/10.51803/yssr.869824

