Bayesian Model Averaging of Chain Event Graphs for Robust Explanatory Modelling

被引:0
作者
Strong, Peter [1 ,3 ]
Smith, Jim Q. [2 ,3 ]
机构
[1] Univ Warwick, Ctr Complex Sci, Coventry, W Midlands, England
[2] Univ Warwick, Dept Stat, Coventry, W Midlands, England
[3] Alan Turing Inst, London, England
来源
INTERNATIONAL CONFERENCE ON PROBABILISTIC GRAPHICAL MODELS, VOL 186 | 2022年 / 186卷
基金
英国工程与自然科学研究理事会; 英国医学研究理事会;
关键词
Graphical Models; Explainable Modelling; Bayesian Model Selection; Chain Event Graphs; Bayesian Model Averaging; Robust Inference; SELECTION;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Chain Event Graphs (CEGs) are a widely applicable class of probabilistic graphical model that can represent context-specific independence statements and asymmetric unfoldings of events in an easily interpretable way. Existing model selection literature on CEGs has largely focused on obtaining the maximum a posteriori (MAP) CEG. However, MAP selection is well-known to ignore model uncertainty. Here, we explore the use of Bayesian model averaging over this class. We demonstrate how this approach can quantify model uncertainty and leads to more robust inference by identifying shared features across multiple high-scoring models. Because the space of possible CEGs is huge, scoring models exhaustively for model averaging in all but small problems is prohibitive. However, we provide a simple modification of an existing model selection algorithm, that samples the model space, to illustrate the efficacy of Bayesian model averaging compared to more standard MAP modelling.
引用
收藏
页数:12
相关论文
共 15 条
  • [1] A Bayesian Hierarchical Model for Criminal Investigations
    Bunnin, F. O.
    Smith, J. Q.
    [J]. BAYESIAN ANALYSIS, 2021, 16 (01): : 1 - 30
  • [2] The R Package stagedtrees for Structural Learning of Stratified Staged Trees
    Carli, Federico
    Leonelli, Manuele
    Riccomagno, Eva
    Varando, Gherardo
    [J]. JOURNAL OF STATISTICAL SOFTWARE, 2022, 102 (06): : 1 - 30
  • [3] Collazo R., 2017, The Dynamic Chain Event Graph
  • [4] Collazo R., 2018, CHAIN EVENT GRAPHS
  • [5] Causal discovery through MAP selection of stratified chain event graphs
    Cowell, Robert G.
    Smith, James Q.
    [J]. ELECTRONIC JOURNAL OF STATISTICS, 2014, 8 : 965 - 997
  • [6] Bayesian Model Averaging: A Systematic Review and Conceptual Classification
    Fragoso, Tiago M.
    Bertoli, Wesley
    Louzada, Francisco
    [J]. INTERNATIONAL STATISTICAL REVIEW, 2018, 86 (01) : 1 - 28
  • [7] Bayesian MAP model selection of chain event graphs
    Freeman, G.
    Smith, J. Q.
    [J]. JOURNAL OF MULTIVARIATE ANALYSIS, 2011, 102 (07) : 1152 - 1165
  • [8] Equivalence classes of staged trees
    Gorgen, Christiane
    Smith, Jim Q.
    [J]. BERNOULLI, 2018, 24 (4A) : 2676 - 2692
  • [9] MODEL SELECTION AND ACCOUNTING FOR MODEL UNCERTAINTY IN GRAPHICAL MODELS USING OCCAMS WINDOW
    MADIGAN, D
    RAFTERY, AE
    [J]. JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION, 1994, 89 (428) : 1535 - 1546
  • [10] Shenvi A, 2019, Arxiv, DOI arXiv:1811.08872