The EM algorithm for graphical association models with missing data

Computational Statistics and Data Analysis

Volumn 19, Issue 2, 1995, Pages 191-201

  Lauritzen, Steffen L ^a  

^a AALBORG UNIVERSITY   (Denmark)

Author keywords

Belief networks; Contingency tables; Decomposable models; Expert systems; Hierarchical models; Latent variables; Probability propagation; Recursive models

Indexed keywords

EID: 58149210716     PISSN: 01679473     EISSN: None     Source Type: Journal    
DOI: 10.1016/0167-9473(93)E0056-A     Document Type: Article

References (49)

1. Multidimensional contingency tables
2. HUGIN — A shell for building Bayesian belief universes for expert systems
3. MUNIN — An EMG assistant
4. Two-demensional contingency tables with both completely and partially cross-classified data
5. The analysis of contingency tables with incompletely classified data
6. Markov fields and log linear models for contingency tables
7. Generalized iterative scaling for log-linear models
8. Additive and multiplicative models and interactions
9. Applications of a general propagation algorithm for probabilistic expert systems
10. Maximum likelihood estimation of observer error-rates using the EM algorithm
11. Maximum likelihood from incomplete data via the EM algorithm (with discussion)
12. Hierarchical interaction models (with discussion)
13. Hierarchical interaction models (with discussion)
14. A modified iterative proportional scaling algorithm for estimation in regular exponential families
15. Decomposition of maximum likelihood in mixed interaction models
16. Maximum likelihood estimation and model selection in contingency tables with missing data
17. Recursive procedures for hierarchical loglinear models on hig--dimensional contingency tables
18. Learning probabilities in causal trees from incomplete databases
19. On use of the EM algorithm for penalized likelihood estimation
20. Log-linear models for frequency tables derived by indirect observation Maximum likelihood equations
21. The analysis of partially categorized contingency data
22. Bayesian updating in causal probabilistic networks by local computation
23. Recursive causal models
24. Graph triangulation — algorithms giving small total state space
25. Optimal decomposition of probabilistic networks by simulated annealing
26. Construction of multilocus genetic linkage maps in humans
27. Lectures on contingency tables
28. Propagation of probabilities means and variances in mixed graphical association models
29. Independence properties of directed Markov fields
30. Local computations with probabilities on graphical structures and their application to expert systems (with discussion)
31. Graphical models for associations between variables some of which are qualitative and some quantitative
32. Maximum likelihood estimation for mixed continuous and categorical data with missing values
33. Axioms for probability and belief-function propagation
34. Bayesian analysis in expert systems
35. Sequential updating of conditional probabilities on directed graphical structures
36. Maximum likelihood theory and applications for distributions generated when observing a function of an exponential family variable
37. Maximum likelihood theory for incomplete data from an exponential family
38. An iterative method for solution of the likelihood equations for incomplete data from exponential families
39. (G)EM algorithms for maximum likelihood in recursive graphical association models
40. Graphical and recursive models for contingency tables
41. On the convergence of the EM algorithm