Extreme dependence for multivariate data

Damien Bosc, Alfred Galichon

    Research output: Contribution to journalArticle

    Abstract

    This article proposes a generalized notion of extreme multivariate dependence between two random vectors which relies on the extremality of the cross-covariance matrix between these two vectors. Using a partial ordering on the cross-covariance matrices, we also generalize the notion of positive upper dependence. We then propose a means to quantify the strength of the dependence between two given multivariate series and to increase this strength while preserving the marginal distributions. This allows for the design of stress-tests of the dependence between two sets of financial variables that can be useful in portfolio management or derivatives pricing.

    Original languageEnglish (US)
    Pages (from-to)1187-1199
    Number of pages13
    JournalQuantitative Finance
    Volume14
    Issue number7
    DOIs
    StatePublished - 2014

    Fingerprint

    Covariance matrix
    Financial variables
    Derivative pricing
    Portfolio management
    Stress test

    Keywords

    • Covariance set
    • Extreme dependence
    • Multivariate dependence

    ASJC Scopus subject areas

    • Economics, Econometrics and Finance(all)
    • Finance

    Cite this

    Extreme dependence for multivariate data. / Bosc, Damien; Galichon, Alfred.

    In: Quantitative Finance, Vol. 14, No. 7, 2014, p. 1187-1199.

    Research output: Contribution to journalArticle

    Bosc, Damien ; Galichon, Alfred. / Extreme dependence for multivariate data. In: Quantitative Finance. 2014 ; Vol. 14, No. 7. pp. 1187-1199.
    @article{641103d965a14835834591a517750139,
    title = "Extreme dependence for multivariate data",
    abstract = "This article proposes a generalized notion of extreme multivariate dependence between two random vectors which relies on the extremality of the cross-covariance matrix between these two vectors. Using a partial ordering on the cross-covariance matrices, we also generalize the notion of positive upper dependence. We then propose a means to quantify the strength of the dependence between two given multivariate series and to increase this strength while preserving the marginal distributions. This allows for the design of stress-tests of the dependence between two sets of financial variables that can be useful in portfolio management or derivatives pricing.",
    keywords = "Covariance set, Extreme dependence, Multivariate dependence",
    author = "Damien Bosc and Alfred Galichon",
    year = "2014",
    doi = "10.1080/14697688.2014.886777",
    language = "English (US)",
    volume = "14",
    pages = "1187--1199",
    journal = "Quantitative Finance",
    issn = "1469-7688",
    publisher = "Routledge",
    number = "7",

    }

    TY - JOUR

    T1 - Extreme dependence for multivariate data

    AU - Bosc, Damien

    AU - Galichon, Alfred

    PY - 2014

    Y1 - 2014

    N2 - This article proposes a generalized notion of extreme multivariate dependence between two random vectors which relies on the extremality of the cross-covariance matrix between these two vectors. Using a partial ordering on the cross-covariance matrices, we also generalize the notion of positive upper dependence. We then propose a means to quantify the strength of the dependence between two given multivariate series and to increase this strength while preserving the marginal distributions. This allows for the design of stress-tests of the dependence between two sets of financial variables that can be useful in portfolio management or derivatives pricing.

    AB - This article proposes a generalized notion of extreme multivariate dependence between two random vectors which relies on the extremality of the cross-covariance matrix between these two vectors. Using a partial ordering on the cross-covariance matrices, we also generalize the notion of positive upper dependence. We then propose a means to quantify the strength of the dependence between two given multivariate series and to increase this strength while preserving the marginal distributions. This allows for the design of stress-tests of the dependence between two sets of financial variables that can be useful in portfolio management or derivatives pricing.

    KW - Covariance set

    KW - Extreme dependence

    KW - Multivariate dependence

    UR - http://www.scopus.com/inward/record.url?scp=84902673798&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84902673798&partnerID=8YFLogxK

    U2 - 10.1080/14697688.2014.886777

    DO - 10.1080/14697688.2014.886777

    M3 - Article

    VL - 14

    SP - 1187

    EP - 1199

    JO - Quantitative Finance

    JF - Quantitative Finance

    SN - 1469-7688

    IS - 7

    ER -