论文信息 - Relaxing the local independence assumption for quantitative learning in acyclic directed graphical models through hierarchical partition models

Relaxing the local independence assumption for quantitative learning in acyclic directed graphical models through hierarchical partition models

The simplest method proposed by Spiegelhalter and Lauritzen (1990) to perform quantitative learning in ADG presents a potential weakness: the local independence assumption. We propose to alleviate this problem through the use of Hierarchical Partition Models. Our approach is compared with the previous one from an interpretative and predictive point of view.

David Madigan | Guido Consonni | Daniela Golinelli

[1] P. Green. Reversible jump Markov chain Monte Carlo computation and Bayesian model determination , 1995 .

[2] Graham J. G. Upton,et al. The Exploratory Analysis of Survey Data Using Log‐Linear Models , 1991 .

[3] D. Madigan,et al. Eliciting prior information to enhance the predictive performance of Bayesian graphical models , 1995 .

[4] D. Madigan,et al. Model Selection and Accounting for Model Uncertainty in Graphical Models Using Occam's Window , 1994 .

[5] J. N. R. Jeffers,et al. Graphical Models in Applied Multivariate Statistics. , 1990 .

[6] Guido Consonni,et al. A Bayesian Method for Combining Results from Several Binomial Experiments , 1995 .

[7] David J. Spiegelhalter,et al. Sequential updating of conditional probabilities on directed graphical structures , 1990, Networks.

[8] David J. Spiegelhalter,et al. Bayesian analysis in expert systems , 1993 .

[9] Donald Malec,et al. Bayesian methodology for combining the results from different experiments when the specifications for pooling are uncertain , 1992 .