Multigraph Representations of Hierarchical Loglinear Models
Document Type
Article
Publication Date
1996
Abstract
We introduce a notion of generator multigraph as an alternative to interaction graphs for the study of hierarchical loglinear models. Generator multigraphs are defined directly from the generator class of the model and are shown to be natural for recognizing decomposable models, obtaining maximum likelihood estimators, and finding conditional independencies in a model. The graph theory involved focuses on maximum spanning trees and edge cutsets (rather than on chordal graphs and minimal vertex separators as with interaction graphs).
Repository Citation
Khamis, H. J.,
& McKee, T. A.
(1996). Multigraph Representations of Hierarchical Loglinear Models. Journal of Statistical Planning and Inference, 53 (1), 63-74.
https://corescholar.libraries.wright.edu/math/151
DOI
10.1016/0378-3758(95)00140-9
