Vector quantile regression beyond the specified case

Guillaume Carlier, Victor Chernozhukov, Alfred Galichon

    Research output: Contribution to journalArticle

    Abstract

    This paper studies vector quantile regression (VQR), which models the dependence of a random vector with respect to a vector of explanatory variables with enough flexibility to capture the whole conditional distribution, and not only the conditional mean. The problem of vector quantile regression is formulated as an optimal transport problem subject to an additional mean-independence condition. This paper provides results on VQR beyond the specified case which had been the focus of previous work. We show that even beyond the specified case, the VQR problem still has a solution which provides a general representation of the conditional dependence between random vectors.

    Original languageEnglish (US)
    Pages (from-to)96-102
    Number of pages7
    JournalJournal of Multivariate Analysis
    Volume161
    DOIs
    StatePublished - Sep 1 2017

    Fingerprint

    Quantile Regression
    Random Vector
    Optimal Transport
    Conditional Distribution
    Regression Model
    Flexibility
    Quantile regression

    Keywords

    • Duality
    • Optimal transport
    • Vector quantile regression

    ASJC Scopus subject areas

    • Statistics and Probability
    • Numerical Analysis
    • Statistics, Probability and Uncertainty

    Cite this

    Vector quantile regression beyond the specified case. / Carlier, Guillaume; Chernozhukov, Victor; Galichon, Alfred.

    In: Journal of Multivariate Analysis, Vol. 161, 01.09.2017, p. 96-102.

    Research output: Contribution to journalArticle

    Carlier, Guillaume ; Chernozhukov, Victor ; Galichon, Alfred. / Vector quantile regression beyond the specified case. In: Journal of Multivariate Analysis. 2017 ; Vol. 161. pp. 96-102.
    @article{6354218f3ad441ccb304f962eb200bab,
    title = "Vector quantile regression beyond the specified case",
    abstract = "This paper studies vector quantile regression (VQR), which models the dependence of a random vector with respect to a vector of explanatory variables with enough flexibility to capture the whole conditional distribution, and not only the conditional mean. The problem of vector quantile regression is formulated as an optimal transport problem subject to an additional mean-independence condition. This paper provides results on VQR beyond the specified case which had been the focus of previous work. We show that even beyond the specified case, the VQR problem still has a solution which provides a general representation of the conditional dependence between random vectors.",
    keywords = "Duality, Optimal transport, Vector quantile regression",
    author = "Guillaume Carlier and Victor Chernozhukov and Alfred Galichon",
    year = "2017",
    month = "9",
    day = "1",
    doi = "10.1016/j.jmva.2017.07.003",
    language = "English (US)",
    volume = "161",
    pages = "96--102",
    journal = "Journal of Multivariate Analysis",
    issn = "0047-259X",
    publisher = "Academic Press Inc.",

    }

    TY - JOUR

    T1 - Vector quantile regression beyond the specified case

    AU - Carlier, Guillaume

    AU - Chernozhukov, Victor

    AU - Galichon, Alfred

    PY - 2017/9/1

    Y1 - 2017/9/1

    N2 - This paper studies vector quantile regression (VQR), which models the dependence of a random vector with respect to a vector of explanatory variables with enough flexibility to capture the whole conditional distribution, and not only the conditional mean. The problem of vector quantile regression is formulated as an optimal transport problem subject to an additional mean-independence condition. This paper provides results on VQR beyond the specified case which had been the focus of previous work. We show that even beyond the specified case, the VQR problem still has a solution which provides a general representation of the conditional dependence between random vectors.

    AB - This paper studies vector quantile regression (VQR), which models the dependence of a random vector with respect to a vector of explanatory variables with enough flexibility to capture the whole conditional distribution, and not only the conditional mean. The problem of vector quantile regression is formulated as an optimal transport problem subject to an additional mean-independence condition. This paper provides results on VQR beyond the specified case which had been the focus of previous work. We show that even beyond the specified case, the VQR problem still has a solution which provides a general representation of the conditional dependence between random vectors.

    KW - Duality

    KW - Optimal transport

    KW - Vector quantile regression

    UR - http://www.scopus.com/inward/record.url?scp=85027234379&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85027234379&partnerID=8YFLogxK

    U2 - 10.1016/j.jmva.2017.07.003

    DO - 10.1016/j.jmva.2017.07.003

    M3 - Article

    VL - 161

    SP - 96

    EP - 102

    JO - Journal of Multivariate Analysis

    JF - Journal of Multivariate Analysis

    SN - 0047-259X

    ER -