Marginal log-linear parameters for graphical Markov models
arXiv:1105.6075 · doi:10.1111/rssb.12020
Abstract
Marginal log-linear (MLL) models provide a flexible approach to multivariate discrete data. MLL parametrizations under linear constraints induce a wide variety of models, including models defined by conditional independences. We introduce a sub-class of MLL models which correspond to Acyclic Directed Mixed Graphs (ADMGs) under the usual global Markov property. We characterize for precisely which graphs the resulting parametrization is variation independent. The MLL approach provides the first description of ADMG models in terms of a minimal list of constraints. The parametrization is also easily adapted to sparse modelling techniques, which we illustrate using several examples of real data.
36 pages
References in corpus (5)
Cited by in corpus (13)
- Constraint-based Causal Discovery from Multiple Interventions over Overlapping Variable Sets
- Graphs for margins of Bayesian networks
- Markovian acyclic directed mixed graphs for discrete data
- The Inflation Technique Completely Solves the Causal Compatibility Problem
- Two algorithms for fitting constrained marginal models
- Log-mean linear models for binary data
- Alternative Markov and Causal Properties for Acyclic Directed Mixed Graphs
- Smoothness of marginal log-linear parameterizations
- Sparse Nested Markov models with Log-linear Parameters
- Dichotomization invariant log-mean linear parameterization for discrete graphical models of marginal independence
- Smooth, identifiable supermodels of discrete DAG models with latent variables
- Causal Effect Identification in Acyclic Directed Mixed Graphs and Gated Models
- Probability Based Independence Sampler for Bayesian Quantitative Learning in Graphical Log-Linear Marginal Models