Ekolojik Çıkarım Yöntemi: 2024 Yılı Ankara Büyükşehir Belediye Başkanlığı Seçimi Oy Geçiş Analizi

Öz

Ekolojik çıkarım yöntemi, bireysel verilere erişimin mümkün olmadığı ya da çok zor olduğu durumlarda, toplulaştırılmış düzeydeki verilerden hareketle bireysel düzeydeki verilere yönelik tahminler yapılmasını sağlayan bir yaklaşımdır. Buradan hareketle, çalışma kapsamında, 2024 yılında yapılan Ankara Büyükşehir Belediye Başkanlığı seçimine ait oy geçişleri Rosen, Jiang, King ve Tanner (2001) tarafından geliştirilen ekolojik çıkarım yaklaşımıyla analiz edilmiştir. Söz konusu oy geçişleri, 8×8 boyutunda kontenjans tablosu temelinde yapılan analiz sonucunda hem seçmen sayısı hem de geçiş olasılık matrisi bazında tahmin edilmiş ve yorumlanmıştır. Elde edilen tahminler, Sankey diyagramı çizilerek görselleştirilmiştir. Ankara Büyükşehir Belediye Başkanlığı seçimi temelinde yapılan analiz sonuçlarına göre, 2019 seçimlerinde Adalet ve Kalkınma Partisi (AK Parti) için oy kullanan seçmenin %54’ünün 2024 seçiminde de AK Parti’ye oy verdiği, 2019 yılı seçiminde AK Parti’ye oy verenlerin yaklaşık %20’sinin 2024 seçiminde oy kullanmadığı, %16,6’sının ise Cumhuriyet Halk Partisi (CHP)’ ne oy verdiği tahmin edilmiştir. Aynı analiz sonuçlarına göre, 2019 seçimlerinde CHP yönünde oy kullanan seçmenin %82,7’sinin yeniden CHP’ye oy verdiği, %10,5’inin oy kullanmadığı, %2,1’inin AK Parti’ye oy verdiği belirlenmiştir. Analizin bir diğer bulgusu ise, 2019 seçiminde oy kullanmayan seçmenin %58,8’inin 2024 yerel seçiminde de oy kullanmamayı tercih ettiği, 2019 yılı seçiminde oy kullanmayan seçmenlerin geriye kalan kısmının %23,5’inin CHP’ye, %1,9’unun AK Parti’ye, %7,8’inin diğer partilere, %2,3’ünün Yeniden Refah Partisi (YRP)’ne, %1,1’i ise İYİ Parti’ye oy verdiği şeklindedir.

Anahtar Kelimeler

• Ekolojik Çıkarım
• Oy Geçişi
• Ankara Büyükşehir Belediye Başkanlığı

Ecological Inference Method: 2024 Ankara Metropolitan Municipality Election Vote Transition Analysis

Öz

The ecological inference method is an approach that allows predictions to be made for individual-level data based on aggregated data when access to individual data is not possible or very difficult. Based on this, within the scope of the study, the vote transitions for the Ankara Metropolitan Municipality elections held in 2024 were analyzed using the ecological inference approach developed by Rosen, Jiang, King, and Tanner (2001). The vote transitions in question were estimated and interpreted based on both the number of voters and the transition probability matrix as a result of the analysis performed based on an 8×8 quota table. The predictions that were obtained were visualized by drawing a Sankey diagram. According to the analysis results based on the Ankara Metropolitan Municipality elections, it was estimated that 54% of the voters who voted for the Justice and Development Party (AK Party) in the 2019 elections also voted for the AK Party in the 2024 elections, approximately 20% of those who voted for the AK Party in the 2019 elections did not vote in the 2024 elections, and 16.6% voted for the Republican People's Party (CHP). According to the same analysis results, it was determined that 82.7% of the voters who voted for the CHP in the 2019 elections voted for the CHP again, 10.5% did not vote, and 2.1% voted for the AK Party. Another finding of the analysis is that 58.8% of the voters who did not vote in the 2019 elections preferred not to vote in the 2024 local elections either and that the remaining 23.5% of the voters who did not vote in the 2019 elections voted for the CHP, 1.9% for the AK Party, 7.8% for other parties, 2.3% for the Yeni Welfare Party (YRP), and 1.1% for the İYİ Party.

Anahtar Kelimeler

• Ecological Inference
• Vote Transition
• Ankara Metropolitan Municipality

Kaynakça

1. Audemard, J. (2024). Understanding vote transfers in two-round elections without resorting to declared data: The contribution of ecological inference, consolidated with factual information from a case study of the 2014 municipal elections in Montpellier. Bulletin of Sociological Methodology/Bulletin de Méthodologie Sociologique, 162(1), 13–34.
2. Barreto, M. A., Collingwood, L., Garcia-Rios, S., & Oskooii, K. A. R. (2019). Estimating candidate support in Voting Rights Act cases: Comparing Iterative EI and EI-R×C methods. Sociological Methods & Research, 51(1), 271–304. https://doi.org/10.1177/0049124119852394
3. Calvo, E,, & Escolar, M, (2003), The local voter: A geographically weighted approach to ecological inference, American Journal of Political Science, 47(1), 189-204.
4. Cataldi, M., Emanuele, V., & Paparo, A. (2012). Elettori in movimento nelle comunali 2011 a Milano, Torino e Napoli. Quaderni Dell’Osservatorio Elettorale Qoe - Ijes, 67(1), 5–43. https://doi.org/10.36253/qoe-9775
5. Çilek Ağacı, (n,d,), Politics / Siyaset, Çilek Ağacı, https://cilekagaci,com/category/politics-siyaset/
6. Gehlke, C. E. (1917). On the correlation between the vote for suffrage and the vote on the liquor question: A preliminary study. Quarterly Publications of the American Statistical Association, 15(117), 524–532.
7. Gregor, K. (2015). Who are Kotleba's voters? Voters' transitions in the Banská Bystrica region in 2009–2014. Sociológia, 47(3).
8. Harrison, X. A. (2015). A comparison of observation-level random effect and beta-binomial models for modelling overdispersion in binomial data in ecology & evolution. PeerJ, 3, e1114. https://doi.org/10.7717/peerj.1114

9. Hudson, I. L., Moore, L., Beh, E. J., & Steel, D. G. (2010). Ecological inference techniques: An empirical evaluation using data describing gender and voter turnout at New Zealand elections, 1893–1919. Journal of the Royal Statistical Society Series A: Statistics in Society, 173(1), 185–213.
10. King, G, (2004), ei: A program for ecological inference, Journal of Statistical Software, 11(7), https://doi,org/10,18637/jss,v011,i07
11. King, G. (1997). Solution to the ecological inference problem: Reconstructing individual behavior from aggregate data. https://doi.org/10.3886/icpsr01132
12. King, G., Rosen, O., & Tanner, M. A. (1999). Binomial-beta hierarchical models for ecological inference. Sociological Methods & Research, 28(1), 61–90. https://doi.org/10.1177/0049124199028001004
13. Klein, J. M. (2019). Estimation of voter transitions in multi-party systems: Quality of credible intervals in (hybrid) multinomial-Dirichlet models (Yayımlanmamış Yüksek lisans tezi). Ludwig-Maximilians-Universität München. Klima, A., Thurner, P. W., Molnar, C., Schlesinger, T., & Küchenhoff, H. (2016). Estimation of voter transitions based on ecological inference: An empirical assessment of different approaches. AStA Advances in Statistical Analysis, 100, 133–159.
14. O’Loughlin, J. (2000). Can King’s ecological inference method answer a social scientific puzzle: Who voted for the Nazi Party in Weimar Germany? Annals of the Association of American Geographers, 90(3), 592–601. https://doi.org/10.1111/0004-5608.00213
15. Ogburn, W. F., & Goltra, I. (1919). How women vote. Political Science Quarterly, 34(3), 413–433. Romero, R., Pavía, J. M., Martín, J., & Romero, G. (2020). Assessing uncertainty of voter transitions estimated from aggregated data: Application to the 2017 French presidential election. Journal of Applied Statistics, 47(13–15), 2711–2736.
16. Rosen, O., Jiang, W., King, G., & Tanner, M. A. (2001). Bayesian and frequentist inference for ecological inference: The R × C case. Statistica Neerlandica, 55(2), 134–156. https://doi.org/10.1111/1467-9574.00162
17. Velimsky, J. A. (2024). Reducing social stratification bias in referendum participation: Evidence from the German local level. Political Research Quarterly, 77(2), 577–591. https://doi.org/10.1177/10659129241230901