Conditional independence collapsibility for acyclic directed mixed graph models

被引:0
|
作者
Li, Weihua [1 ]
Sun, Yi [1 ,2 ]
Heng, Pei [2 ]
机构
[1] Xinjiang Univ, Coll Math & Syst Sci, Urumqi 830000, Xinjiang, Peoples R China
[2] Northeast Normal Univ, KLAS, Changchun 130024, Jilin, Peoples R China
关键词
Acyclic directed mixed graph; Conditional independence collapsibility; Directed acyclic graph; Graphical model; DAG MODELS; MARKOV PROPERTIES;
D O I
10.1016/j.ijar.2024.109208
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Collapsibility refers to the property that, when marginalizing over some variables that are not of interest from the full model, the resulting marginal model of the remaining variables is equivalent to the local model induced by the subgraph on these variables. This means that when the marginal model satisfies collapsibility, statistical inference results based on the marginal model and the local model are consistent. This has significant implications for small -sample data, modeling latent variable data, and reducing the computational complexity of statistical inference. This paper focuses on studying the conditional independence collapsibility of acyclic directed mixed graph (ADMG) models. By introducing the concept of inducing paths in ADMGs and exploring its properties, the conditional independence collapsibility of ADMGs is characterized equivalently from both graph theory and statistical perspectives.
引用
收藏
页数:11
相关论文
共 50 条
  • [21] Collapsibility of contingency tables based on conditional models
    Vellaisamy, P.
    Vijay, V.
    JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 2010, 140 (05) : 1243 - 1255
  • [22] Analyzing directed acyclic graph recombination
    Cotta, C
    Troya, JM
    COMPUTATIONAL INTELLIGENCE: THEORY AND APPLICATIONS, PROCEEDINGS, 2001, 2206 : 739 - 748
  • [23] Implementation of directed acyclic word graph
    Balík, M
    KYBERNETIKA, 2002, 38 (01) : 91 - 103
  • [24] Hierarchical directed acyclic graph kernel
    NIT Communication Science Laboratories, NTT Corporation, Kyoto, 619-0237, Japan
    不详
    不详
    Syst Comput Jpn, 2006, 10 (58-68):
  • [25] How to layer a directed acyclic graph
    Healy, P
    Nikolov, NS
    GRAPH DRAWING, 2002, 2265 : 16 - 30
  • [27] Causal effect identification in acyclic directed mixed graphs and gated models
    Pena, Jose M.
    Bendtsen, Marcus
    INTERNATIONAL JOURNAL OF APPROXIMATE REASONING, 2017, 90 : 56 - 75
  • [28] Hierarchical multivariate directed acyclic graph autoregressive models for spatial diseases mapping
    Gao, Leiwen
    Datta, Abhirup
    Banerjee, Sudipto
    STATISTICS IN MEDICINE, 2022, 41 (16) : 3057 - 3075
  • [29] Directed Acyclic Graph-Based Technology Mapping of Genetic Circuit Models
    Roehner, Nicholas
    Myers, Chris J.
    ACS SYNTHETIC BIOLOGY, 2014, 3 (08): : 543 - 555
  • [30] A characterization of moral transitive acyclic directed graph Markov models as labeled trees
    Castelo, R
    Siebes, A
    JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 2003, 115 (01) : 235 - 259