Pearl’in Nedensel Modelinin Ampirik Araştırmadaki Rolü

Yıl 2024, Cilt: 13 Sayı: 2, 230 - 252, 11.09.2024

Fırat Bilgel

Öz

Bu çalışma, korelasyonları tespit etmek yerine neden-sonuç ilişkilerini açıklığa kavuşturan kesin araştırma soruları formüle etmenin gerekliliğini vurgulamakta ve karmaşık nedensel sorularla baş etmede, nedensel grafikler veya yapısal nedensel modeller olmadan sadece regresyon analizi kullanmanın tehlikelerine dikkat çekmektedir. Judea Pearl'ün nedensel epistemolojisinde kullanılan, nedensel grafikler, yapısal nedensel modeller ve do-kalkülüs gibi araçları nedensel etkileri tahmin etmek için tanıtır. Çalışma aynı zamanda karıştırıcı ve çarpışma etkileriyle ilgili zorluklara, Hukuk ve Ekonomi’den basit örneklerle, do-kalkülüs uygulamalarına ve tahdit temelli algoritmalar aracılığıyla nedensel keşif yöntemlerindeki gelişmelere değinmektedir. Makale ayrıca etki tanımlama ve tahmin konusunda en iyi uygulamalar hakkında kısa bir yol haritası sunar.

Anahtar Kelimeler

Pearl'ün Nedensel Epistemolojisi, Nedensel Keşif, Etki tanımlama

The Role of Pearl’s Causal Framework in Empirical Research

Öz

This paper underscores the necessity of formulating precise research questions that clarify causal relationships rather than simply identifying correlations and highlights the perils of relying solely on regression analysis in tackling complex causal inquiries without causal diagrams or structural causal models. It introduces Judea Pearl's causal epistemology, including causal graphs, structural causal models, and do-calculus as vital tools for estimating causal effects. It extends to the challenges of confounding and collider effects, the application of do-calculus with basic examples from Law & Economics and the advancements in causal discovery methods through constraint-based algorithms. The paper also offers a brief roadmap on best practices for identification and estimation.

Anahtar Kelimeler

Pearl's Causal Epistemology, Causal Discovery, Identification

Kaynakça

• Badsha, M. B., Martin, E. A., and Fu, A. Q. (2021). MRPC: An R package for inference of causal graphs. Frontiers in Genetics, 12:651812.
• Bareinboim, E., Correa, J. D., Ibeling, D., and Icard, T. (2022). In H. Geffner, R. Dechter, and J. Y. Halpern (Eds.). Probabilistic and Causal Inference: The Works of Judea Pearl (1st. ed., pp. 507–556). New York: ACM Books, Vol. 36. Association for Computing Machinery.
• Bareinboim, E. and Pearl, J. (2016). Causal inference and the data-fusion problem. In Shiffrin, R. M. (Ed.). Proceedings of the National Academy of Sciences, 113, 7345–7352.
• Barrett, M. (2024). ggdag: Analyze and Create Elegant Directed Acyclic Graphs. R package version 0.2.12, https://r-causal.github.io/ggdag/.
• Chickering, D. M. (2002). Optimal structure identification with greedy search. Journal of machine learning research, 3(Nov), 507–554.
• Cinelli, C. and Hazlett, C. (2020). Making sense of sensitivity: Extending omitted variable bias. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 82(1), 39–67.
• Colombo, D., Maathuis, M. H., Kalisch, M., and Richardson, T. S. (2012). Learning high-dimensional directed acyclic graphs with latent and selection variables. The Annals of Statistics, 40 (1), 294–321.
• Holland, P. W. (1986). Statistics and causal inference. Journal of the American Statistical Association, 81(396), 945–960.
• Huang, Y. and Valtorta, M. (2012). Pearl’s calculus of intervention is complete. arXiv preprint arXiv:1206.6831. Hünermund, P. and Bareinboim, E. (2023). Causal inference and data fusion in econometrics. The Econometrics Journal, page utad008.
• Iannone, R. and Roy, O. (2024). DiagrammeR: Graph/Network Visualization. R package version 1.0.11.9000, https://github.com/rich-iannone/DiagrammeR.
• Imbens, G.W., Rubin, D.B. (2010). Rubin Causal Model. In: Durlauf, S.N., Blume, L.E. (Eds.) Microeconometrics. (pp. 229–241). London: The New Palgrave Economics Collection. Palgrave Macmillan.
• Kalisch, M., Mächler, M., Colombo, D., Maathuis, M. H., and Bühlmann, P. (2012). Causal inference using graphical models with the R package pcalg. Journal of statistical software, 47, 1–26.
• Meek, C. (1997). Graphical Models: Selecting causal and statistical models. Ph.d thesis, Carnegie Mellon University.
• Nogueira, A. R., Pugnana, A., Ruggieri, S., Pedreschi, D., and Gama, J. (2022). Methods and tools for causal discovery and causal inference. Wiley interdisciplinary reviews: data mining and knowledge discovery, 12(2): e1449.
• Novak, A., Boutwell, B. B., and Smith, T. B. (2023). Taking the problem of colliders seriously in the study of crime: A research note. Journal of Experimental Criminology, 1–10.
• Pearl, J. (1988). Probabilistic reasoning in intelligent systems. San Mateo, CA: Morgan Kaufmann.
• Pearl, J. (1995). Causal diagrams for empirical research. Biometrika, 82(4), 669–688.
• Pearl, J. (2009). Causality: Models, Reasoning and Inference (2nd ed.). New York, NY: Cambridge University Press.
• Pearl, J., Glymour, M., and Jewell, N. P. (2016). Causal inference in statistics: A primer. John Wiley & Sons.
• Pearl, J. and Mackenzie, D. (2018). The book of why: the new science of cause and effect. Basic Books.
• Petersen, A. H. (2022). causalDisco: Tools for Causal Discovery on Observational Data. R package version 0.9.1.
• R Core Team (2024). R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria.
• Ramsey, J. and Andrews, B. (2023). Py-Tetrad and RPy-Tetrad: A new Python interface with R support for tetrad causal search. Proceedings of Machine Learning Research (PMLR), Causal Analysis Workshop Series, 223, 40-51.
• Rubin, D. (2005). Causal inference using potential outcomes: Design, modeling, decisions. Journal of the American Statistical Association, 100 (469), 322–331.
• Sachs, M. C., Jonzon, G., Sjölander, A., and Gabriel, E. E. (2023). A general method for deriving tight symbolic bounds on causal effects. Journal of Computational and Graphical Statistics, 32(2), 567–576.
• Scheines, R., Spirtes, P., Glymour, C., Meek, C., and Richardson, T. (1998). The tetrad project: Constraint based aids to causal model specification. Multivariate Behavioral Research, 33(1), 65–117.
• Scutari, M., Silander, T., and Ness, R. (2024). bnlearn: Bayesian Network Structure Learning, Parameter Learning and Inference. R package version 4.9.4.
• Sekhon, J. S. (2010). The Statistics of Causal Inference in the Social Sciences. Political Science 236A and Statistics 239A Lecture Notes, Berkeley Political Science.
• Spirtes, P. and Glymour, C. (1991). An algorithm for fast recovery of sparse causal graphs. Social science computer review, 9(1), 62–72.
• Spirtes, P., Glymour, C., and Scheines, R. (1993). Causation, Prediction, and Search. Lecture notes in Statistics. Springer.
• Spirtes, P., Glymour, C., and Scheines, R. (2000). Causation, prediction, and search. MIT Press Books, 1.
• Spirtes, P., Meek, C., and Richardson, T. (1999). An algorithm for causal inference in the presence of latent variables and selection bias. Computation, causation, and discovery, 21, 1–252
• Textor, J., Van der Zander, B., Gilthorpe, M., Liśkiewicz, M., and Ellison, G. (2016). Robust causal inference using directed acyclic graphs: the R package dagitty. International journal of epidemiology, 45(6), 1887–1894.
• Tikka, S., Hyttinen, A., and Karvanen, J. (2021). Causal effect identification from multiple incomplete data sources: A general search-based approach. Journal of Statistical Software, 99, 1–40.
• Tikka, S. and Karvanen, J. (2017). Identifying causal effects with the R package causal effect. Journal of Statistical Software, 76(12), 1–30.
• Wang, X., Jiang, Y., Zhang, N., and Small, D. (2018). Sensitivity analysis and power for instrumental variable studies. Biometrics, 74(4), 1150–1160.