The likelihood approach to statistics can be interpreted as a theory of fuzzy probability. This paper presents a generalization of credal networks obtained by generalizing imprecise probabilities to fuzzy probabilities; that is, by additionally considering the relative plausibility of different values in the probability intervals.
Keywords. Bayesian networks, credal networks, graphical models, d-separation, imprecise probabilities, updating, likelihood function, hierarchical model, fuzzy probabilities.
Paper Download
The paper is availabe in the following formats:
Plenary talk : Press here to get the file of the presentation.
Poster : Press here to get the file of the poster.
Authors addresses:
Ludwig-Maximilians-University Munich
E-mail addresses:
| Marco Cattaneo | cattaneo@stat.uni-muenchen.de |