Modeling Asymmetric Relationships from Symmetric Networks

Arturas Rozenas, Shahryar Minhas, John Ahlquist

    Research output: Contribution to journalArticle

    Abstract

    Many bilateral relationships requiring mutual agreement produce observable networks that are symmetric (undirected). However, the unobserved, asymmetric (directed) network is frequently the object of scientific interest. We propose a method that probabilistically reconstructs the latent, asymmetric network from the observed, symmetric graph in a regression-based framework. We apply this model to the bilateral investment treaty network. Our approach successfully recovers the true data generating process in simulation studies, extracts new, politically relevant information about the network structure inaccessible to alternative approaches, and has superior predictive performance.

    Original languageEnglish (US)
    Pages (from-to)231-236
    Number of pages6
    JournalPolitical Analysis
    Volume27
    Issue number2
    DOIs
    StatePublished - Apr 1 2019

    Fingerprint

    treaty
    regression
    simulation
    performance

    Keywords

    • Bayesian estimation
    • binary responses
    • latent variables
    • networks

    ASJC Scopus subject areas

    • Sociology and Political Science
    • Political Science and International Relations

    Cite this

    Modeling Asymmetric Relationships from Symmetric Networks. / Rozenas, Arturas; Minhas, Shahryar; Ahlquist, John.

    In: Political Analysis, Vol. 27, No. 2, 01.04.2019, p. 231-236.

    Research output: Contribution to journalArticle

    Rozenas, A, Minhas, S & Ahlquist, J 2019, 'Modeling Asymmetric Relationships from Symmetric Networks', Political Analysis, vol. 27, no. 2, pp. 231-236. https://doi.org/10.1017/pan.2018.41
    Rozenas, Arturas ; Minhas, Shahryar ; Ahlquist, John. / Modeling Asymmetric Relationships from Symmetric Networks. In: Political Analysis. 2019 ; Vol. 27, No. 2. pp. 231-236.
    @article{5552086d3adc4fdaaadc97625af66b9b,
    title = "Modeling Asymmetric Relationships from Symmetric Networks",
    abstract = "Many bilateral relationships requiring mutual agreement produce observable networks that are symmetric (undirected). However, the unobserved, asymmetric (directed) network is frequently the object of scientific interest. We propose a method that probabilistically reconstructs the latent, asymmetric network from the observed, symmetric graph in a regression-based framework. We apply this model to the bilateral investment treaty network. Our approach successfully recovers the true data generating process in simulation studies, extracts new, politically relevant information about the network structure inaccessible to alternative approaches, and has superior predictive performance.",
    keywords = "Bayesian estimation, binary responses, latent variables, networks",
    author = "Arturas Rozenas and Shahryar Minhas and John Ahlquist",
    year = "2019",
    month = "4",
    day = "1",
    doi = "10.1017/pan.2018.41",
    language = "English (US)",
    volume = "27",
    pages = "231--236",
    journal = "Political Analysis",
    issn = "1047-1987",
    publisher = "Oxford University Press",
    number = "2",

    }

    TY - JOUR

    T1 - Modeling Asymmetric Relationships from Symmetric Networks

    AU - Rozenas, Arturas

    AU - Minhas, Shahryar

    AU - Ahlquist, John

    PY - 2019/4/1

    Y1 - 2019/4/1

    N2 - Many bilateral relationships requiring mutual agreement produce observable networks that are symmetric (undirected). However, the unobserved, asymmetric (directed) network is frequently the object of scientific interest. We propose a method that probabilistically reconstructs the latent, asymmetric network from the observed, symmetric graph in a regression-based framework. We apply this model to the bilateral investment treaty network. Our approach successfully recovers the true data generating process in simulation studies, extracts new, politically relevant information about the network structure inaccessible to alternative approaches, and has superior predictive performance.

    AB - Many bilateral relationships requiring mutual agreement produce observable networks that are symmetric (undirected). However, the unobserved, asymmetric (directed) network is frequently the object of scientific interest. We propose a method that probabilistically reconstructs the latent, asymmetric network from the observed, symmetric graph in a regression-based framework. We apply this model to the bilateral investment treaty network. Our approach successfully recovers the true data generating process in simulation studies, extracts new, politically relevant information about the network structure inaccessible to alternative approaches, and has superior predictive performance.

    KW - Bayesian estimation

    KW - binary responses

    KW - latent variables

    KW - networks

    UR - http://www.scopus.com/inward/record.url?scp=85063571015&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85063571015&partnerID=8YFLogxK

    U2 - 10.1017/pan.2018.41

    DO - 10.1017/pan.2018.41

    M3 - Article

    VL - 27

    SP - 231

    EP - 236

    JO - Political Analysis

    JF - Political Analysis

    SN - 1047-1987

    IS - 2

    ER -