Kantil regresyon karma model ile sosyal bağlılık endeksinin heterojenliğinin incelenmesi

Öz

Çalışmanın amacı, Ekonomik Kalkınma ve İşbirliği Örgütü (OECD)’ne üye ülkelerin arasındaki sosyal bağlılık yapısının görselleştirilmesi ve ülkelerdeki sosyo-demografik, ekonomik, din ve resmi dil faktörlerinin Sosyal Bağlılık Endeksine (SCI) etkisinin parametrik olmayan bir yöntemle incelenmesidir. Çalışmadaki veriseti 3 farklı veri kaynağından alınmıştır: Dünya Bankası, OECD ve Facebook. Facebook firmasından alınan veriler OECD üye ülkeleri arasındaki sosyal ağ yapısının görselleştirilmesi ve özelliklerinin anlaşılması için kullanılmıştır. Ek olarak veri kaynaklarından alınan tüm verilerin birleştirilmesiyle elde edilen kümüle veri seti, SCI’ya etki eden faktörlerin Kantil Regresyon Karma Modeller (QRMIX) ile belirlenmesi amacıyla kullanılmıştır. QRMIX sonucunda, SCI’ya etkisi farklılaşan 4 küme belirlenmiştir. Önem derecesi analizine göre, SCI’nın düşük seviyelerinde ülkenin resmi dini önemi en düşük faktör iken SCI’nın yüksek seviyelerinde en önemli ikinci faktördür. Benzer yaş, eğitim seviyesi, dil ve dine mensup ülkeler arasında güçlü bir sosyal ağ yapısı olduğu gösterilmiştir. Ayrıca, literatürdeki çalışmalarda benzer sosyal ağ gücüne sahip ülkelerarasında ekonomik olarak da güçlü bir bağ olduğu gösterilmiştir. Bu çalışmada da, SCI değerinin farklı kantillerine göre bağımsız faktörlerin öneminin değiştiği, bu sebeple farklı sosyal bağlantılara sahip ülkelerin ithalat-ihracat ve finansal işlemler gibi göstergeleri için farklı aksiyon planları oluşturulabileceği önerilmiştir. Sonuç olarak, bu çalışma farklı bağlantı gücüne sahip OECD ülkeleri için politika yapıcılarına yardımcı olabilir.

Anahtar Kelimeler

• Kantil regresyon karma modeller
• Sosyal bağlılık endeksi
• Parametrik olmayan yöntemler
• Sosyal ağ analizi

Assessing the heterogeneity of social connectedness index via quantile regression mixture model

Öz

This study aims to visualize a network of Social Connectedness Index (SCI) in Organization for Economic Co-operation and Development (OECD) countries and then explores the importance of sociodemographic, economic, religion, and distance metrics between countries on SCI using a non-parametric test. The final dataset is aggregated from 3 different data sources: Worldbank, OECD, and Facebook. Drawing upon a data set from Facebook Inc. is used to visualize and understand the network structure among OECD countries. Furthermore, the aggregated dataset used in this study is the first usage of Quantile Regression Mixture Models (QRMIX) to determine factors affecting SCI. As a result of the QRMIX model, 4 clusters are identified in different quantiles where the impact of independent factors are differentiated. Based on the variable importance analysis, almost the least important variable at the lower level of SCI value is religion while it is the second most important factor at the highest level of SCI value. SCI mostly shows up as strong relationships between countries with residents of similar ages and education levels where using common language and having same religions, as well. Also, based on the literature review, it is shown that countries with a higher proportion of similar connections to other countries have more positive economic connections among OECD countries. Thus, given the variable importance of SCI for different subgroups of based on SCI quantiles, this study suggests that different action plans about improving importexport and other financial transactions for the country pairs might be created. To sum up, according to different social connection power of OECD countries, this study can help policymakers.

Anahtar Kelimeler

• Quantile regression mixture models
• Social connectedness index
• Non-Parametric method
• Social network analysis

Kaynakça

1. [1] Abraham A, Hassanien AE, Snasel V. Computational Social Network Analysis: Trends, Tools and Research Advances. Dordrecht, Netherlands, Springer, 2010.
2. [2] Bailey M, Cao R, Kuchler T, Stroebel J, Wong A. “Measuring Social Connectedness”. National Bureau of Economic Research, Cambridge, USA, 23608, 2017.
3. [3] Bailey M, Kuchler T, Russel D, State B, Stroebel J. “The Determinants and Effects of Social Connectedness in Europe”. Center for Economic Studies and Ifo Institute (CESifo), Munich, Germany, 8310, 2020.
4. [4] Baker M. “The impact of social networking sites on politics”. The Review: A Journal of Undergraduate Student Research, 10(1), 72-74, 2009.
5. [5] De Brun A, McAuliffe E. “Social network analysis as a methodological approach to explore health systems: a case study exploring support among senior managers/executives in a hospital network”. International Journal of Environmental Research and Public Health, 15(3), 1-11, 2018.
6. [6] Drakulich KM. “Social capital, information, and perceived safety from crime: the differential effects of reassuring social connections and vicarious victimization”. Social Science Quarterly, 96(1), 176-190, 2015.
7. [7] Erisen E, Erisen C. “The effect of social networks on the quality of political thinking”. Political Psychology, 33(6), 839-865, 2012.
8. [8] Facebook Inc. “Social Connectedness Index”. https://dataforgood.fb.com/tools/social-connectednessindex/ (01.02.2020).

9. [9] Rauch JE. “Business and social networks in international trade”. Journal of Economic Literature, 39(4), 1177-1203, 2001.
10. [10] Wagner D, Head K, Ries J. “Immigration and the trade of provinces”. Scottish Journal of Political Economy, 49(5), 507-525, 2002.
11. [11] Danis WM, Clercq DD, Petricevic O. “Are social networks more important for new business activity in emerging than developed economies? An empirical extension”. International Business Review, 20(4), 394-408, 2011.
12. [12] Combes P-P, Lafourcade M, Mayer T. “The Trade-Creating effects of business and social networks: evidence from France”. Journal of International Economics, 66(1), 1-29, 2005.
13. [13] Paniagua J, Korzynski P, Mas-Tur A. “Crossing borders with social media: Online social networks and FDI”. European Management Journal, 35(3), 314-326, 2017.
14. [14] Gao T. “Ethnic Chinese networks and international investment: evidence from inward FDI in China”. Journal of Asian Economics, 14(4), 611-629, 2003.
15. [15] Forstenlechner I, Mellahi K. “Gaining legitimacy through hiring local workforce at a premium: The case of MNEs in the United Arab Emirates”. Journal of World Business, 46(4), 455-461, 2011.
16. [16] Hua J, Huang M, Huang C. “Centrality metrics’ performance comparisons on stock market datasets”. Symmetry, 11(7), 1-15, 2019.
17. [17] Hunter DR, Young DS. “Semiparametric mixtures of regressions”. Journal of Nonparametric Statistics, 24(1), 19-38, 2012.
18. [18] Javed M, Tuckova Z, Jibril AB. “The role of social media on tourists’ behavior: an empirical analysis of millennials from the czech republic”. Sustainability, 12(18), 1-19, 2020.
19. [19] Kalantan ZI, Einbeck J. “Quantile-Based estimation of the finite cauchy mixture model”. Symmetry, 11(9), 1-19, 2019.
20. [20] Kılıç Depren S, Gökalp Yavuz F. “The network analysis of the domestic and international air transportation structure of Turkey”. Mugla Journal of Science and Technology, 4(2), 148-155, 2018.
21. [21] Kılıç Depren S. “Determination of the factors affecting students’ science achievement level in Turkey and Singapore: An application of quantile regression mixture model”. Journal of Baltic Science Education, 19(2), 247-260, 2020.
22. [22] Kuchler T, Russel D, Stroebel J. “The Geographic Spread of Covid-19 Correlates with the Structure of Social Networks as Measured by Facebook”. National Bureau of Economic Research, Cambridge, USA, 26990, 2020.
23. [23] Kuchler Li Y, Peng L, Stroebel J, Zhou D. “Social Proximity to Capital: Implications for Investors and Firms”. National Bureau of Economic Research, Cambridge, USA, 27229, 2020.
24. [24] Koenker R, Bassett G. “Regression quantiles”. Econometrica, 46, 33-50, 1978.
25. [25] McLachlan GJ, Peel D. Finite Mixture Models. 1st ed. New York, USA, John Wiley & Sons, 2000.
26. [26] Organization for Economic Co-operation and Development. “Data”. https://data.oecd.org/ (01.02.2020).
27. [27] Raza N, Shahzad SJH, Tiwari AK, Shahbaz M. “Asymmetric impact of gold, oil prices and their volatilities on stock prices of emerging markets”. Resources Policy, 49, 290-301, 2016.
28. [28] Richard JW, Ching-Ray Y, Emir B, Zou KH, Cabrera J. “A Comparison and Integration of Quantile Regression and Finite Mixture Modeling”. Joint Statistical Meeting, Boston, USA, 2-7 August 2014.
29. [29] Small ML. “Racial differences in networks: do neighborhood conditions matter?”. Social Science Quarterly, 88(2), 320-343, 2007.
30. [30] Smithson M, Shou Y. “CDF-Quantile distributions for modelling random variables on the unit interval”. British Journal of Mathematical and Statistical Psychology, 70, 412-438, 2017.
31. [31] World Bank. “DataBank”. http://databank.worldbank.org/data/home.aspx (01.02.2020)
32. [32] Weare C, Loges WE, Oztas N. “Email effects on the structure of local associations: a social network analysis”. Social Science Quarterly, 88(1), 222-243, 2007.
33. [33] Wu Q, Yao W. “Mixtures of quantile regressions”. Computational Statistics & Data Analysis, 93, 162-176, 2016.
34. [34] Yum S. “Social Network Analysis for Coronavirus (COVID19) in the United States”. Social Science Quarterly, 101(4), 1642-1647, 2020.
35. [35] Zivkovic R, Gajic J, Brdar I. “The impact of social media on tourism”. Sinteza, 1, 758-761, 2014.