Journals / The Journal of International Scientific Researches / 2019 / Cilt: 4 Sayı: 3

Incorrect Model Selection Of AIC Value When Determining Copula Model

Kapula Modelinin Belirlenmesinde AIC Değerinin Hatalı Seçimi

Mervenur Pala(ONDOKUZ MAYIS ÜNİVERSİTESİ)
Fatih Sağlam(ONDOKUZ MAYIS ÜNİVERSİTESİ)0000-0002-2084-2008
Çağlar Sözen(GİRESUN ÜNİVERSİTESİ)0000-0002-3732-5058
Pages
335–343
Publication Date
2019-10-22
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

In addition, the predisposition to select incorrect Copula families has been revealed.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Copulas are functions that reveal the dependence between random variables, have uniform distribution on univariate margins [0,1] and link multivariate distributions to their univariate margins.
📊
Key Findings & Data:When establishing the dependency structure with Copula, different models should be established and the appropriate one among them should be preferred.
💡
Conclusion & Impact:In addition, the predisposition to select incorrect Copula families has been revealed.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Kapula · AIC · Model Seçimi

Abstract

Copulas are functions that reveal the dependence between random variables, have uniform distribution on univariate margins [0,1] and link multivariate distributions to their univariate margins. When establishing the dependency structure with Copula, different models should be established and the appropriate one among them should be preferred. There are different criteria used to make this choice. Among these criteria, the most preferred AIC value may lead to the selection of incorrect Copula model at different observation numbers and different correlation levels. In order to understand this problem better, model choices made in different combinations according to AIC value were examined. Incorrect selections in the models are discussed in detail. In addition, the predisposition to select incorrect Copula families has been revealed.

Özet

Kapulalar, tesadüfi değişkenler arasındaki bağımlılığı ortaya koyan, tek değişkenli marjinalleri [0,1] üzerinde düzgün dağılıma sahip ve çok değişkenli dağılımları kendi tek değişkenli marjinallerine bağlayan fonksiyonlardır. Kapula ile bağımlılık yapısı ortaya konulurken, farklı modeller kurularak aralarından uygun olan tercih edilmelidir. Bu tercih yapılırken kullanılan farklı kriterler mevcuttur. Bu kriterler arasında en çok tercih edilen AIC değeri, farklı gözlem sayılarında ve farklı ilişki seviyelerinde hatalı Kapula modelinin seçilmesine neden olabilmektedir. Bu problemi daha iyi anlamak amacıyla, AIC değerine göre farklı kombinasyonlarda yapılan model tercihleri incelenmiştir. Modeller içerisindeki hatalı tercihler ayrıntılı biçimde ele alınmıştır. Ayrıca hatalı Kapula ailelerini seçmeye yönelik yatkınlıklar ortaya konulmuştur.

🔖

Cite This Article

Sağlam, F., Sözen, Ç. (2019). Incorrect Model Selection Of AIC Value When Determining Copula Model. The Journal of International Scientific Researches, Cilt: 4 Sayı: 3, 335–343. https://doi.org/10.23834/isrjournal.628779

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (8)

  1. Akaike, H. (1974). A new look at the statistical model identification. In Selected Papers of Hirotugu Akaike, Springer, New York, NY, 215-222.
  2. Cherubini, U., Luciano, E. and Vecchiato, W. 2004. Copula methods in finance. John Wiley and Sons, New York, 289.
  3. Fang, Y., Madsen, L., & Liu, L. (2014). Comparison of Two Methods to Check Copula Fitting. International Journal of Applied Mathematics, 44(1).
  4. Genest, C., Quesada Molina, J. J. and Rodríguez Lallena, J. A. 1995. De l'impossibilité de construire des lois à marges multidimensionnelles données à partir de copules. Comptes rendus de l'Académie des sciences. Série 1, Mathématique, 320(6), 723-726.
  5. Jordanger, L. A., & Tjøstheim, D. (2014). Model selection of copulas: AIC versus a cross validation copula information criterion. Statistics & Probability Letters, 92, 249-255.
  6. Kaishev, V. K., Dimitrova, D. S. and Haberman, S. 2007. Modelling the joint distribution of competing risks survival times using copula functions. Insurance: Mathematics and Economics, 41(3), 339-361.
  7. Sklar, A. 1959. Fonctions de Répartition à n Dimensions et Leurs Marges. Publ. Inst. Statist. Univ., 8, 229-231.
  8. Trivedi, P. K. and Zimmer, D. M. 2005. Copula modeling: An introduction for practitioners. Publishers Inc., 28, Hanover, USA.