SavedAdd your journal

Journals / Anadolu Üniversitesi Bilim ve Teknoloji Dergisi :A-Uygulamalı Bilimler ve Mühendislik / 2004 / Cilt: 5 - Sayı: 2

Graphical models for discrete variables

Kesikli değişken içeren grafiksel modeller

Fikri GÖKPINAR
Hülya BAYRAK
Pages
195–200
Publication Date
2022-10-11
DOI
—
🏛️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 this study, deviance, which is used to test conditional independencies, is studied.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Graphical models arise from restrictions that are expressible as conditional independencies of variables pairs.
📊
Key Findings & Data:Graphical model is a subclass of hierarchical log linear models.
💡
Conclusion & Impact:In this study, deviance, which is used to test conditional independencies, is studied.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Abstract

Graphical models arise from restrictions that are expressible as conditional independencies of variables pairs. Graphical model is a subclass of hierarchical log linear models. These models can be represented by an undirected graph. Hierarchical log linear model has a set of minimal sufficient statistics, which is a set of proper marginal contingency tables. In this study, deviance, which is used to test conditional independencies, is studied.

Özet

Grafiksel modeller değişken çiftlerinin koşullu bağımsızlıkları ile açıklanan kısıtlarla belirlenir. Grafiksel model hiyerarşik loglineer modellerin bir alt sınıfıdır. Bu modeller yön verilmemiş grafikle gösterilebilir. Hiyerarşik loglineer model minimal yeterli istatistiklerin bir kümesine sahiptir. Bu küme marjinal olumsallık tablolarının bir kümesidir. Bu çalışmada koşullu bağımsızlıkların test işleminde kullanılan sapma ifadesi irdelenmiştir.

🔖

Cite This Article

GÖKPINAR, F., BAYRAK, H. (2022). Graphical models for discrete variables. Anadolu Üniversitesi Bilim ve Teknoloji Dergisi :A-Uygulamalı Bilimler ve Mühendislik, Cilt: 5 - Sayı: 2, 195–200. https://ajindex.com/articles/438444

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (3)

  1. Bayrak, H., and Erbaş, S. (1998). Different patterns with zero partial association for five variables. Far East Journal of Theoretical Statistics 2( 1), 95-103
  2. Bleckert, G., Oppel U.G., Salzsieder E. (1998). Mixed graphical models for simultaneous model identi­fication and control applied to glucose-insulin metabolism. Computer Methods and Programs in Biomedicine 56, 141-155 3. Edwards, D. (2001). Introduction to Graphical Model­ling. 2nd Edition, Springer-Verlag, New York 4. Edwards, D. And Havranek A. (1985). Afast procedure for model search in multidimensional contin­gency tables. Biometrica 72, 339-351 5. Edwards, D. And Kreiner, S., 1983, The analysis of contingency tables by graphical models. Biomet­rica, 70, 553-62 6. Lauritzen S.L. (1996). Graphical Models, Clarendon press, London 7. Lauritzen S.L. (1989). Lectures on contingency tables (3rd edn), Technical report R-89-29, Institute for Electronic Systems, Aalborg University 8. Mühlenbein, H., Mahnig, T. (2000). Evolutionary Op­timization Using Graphical Models, New Gen­eration Computing, Ohmsha, pp.157-165
  3. Reinis, Z. vd. (1981). Prognostic significance of the risk profile inde prevention of coronary heart deisease (in Czech). Bratis. Let Listy 76, 136-150