Tail asymptotics for the bivariate skew normal

Thomas Fung, Eugene Seneta

    Research output: Contribution to journalArticleResearchpeer-review

    Abstract

    We derive the asymptotic rate of decay to zero of the tail dependence of the bivariate skew normal distribution under the equal-skewness condition α12, =α, say. The rate depends on whether α>0 or α<0. For the lower tail, the latter case has rate asymptotically identical with the bivariate normal (α=0), but has a different multiplicative constant. The case α>0 gives a rate dependent on α. The detailed asymptotic behaviour of the quantile function for the univariate skew normal is a key. This study is partly a sequel to our earlier one on the analogous situation for bivariate skew t.

    LanguageEnglish
    Pages129-138
    Number of pages10
    JournalJournal of Multivariate Analysis
    Volume144
    DOIs
    Publication statusPublished - 1 Feb 2016

    Fingerprint

    Tail Asymptotics
    Normal distribution
    Skew
    Tail Dependence
    Skew-normal Distribution
    Quantile Function
    Bivariate Distribution
    Skewness
    Univariate
    Asymptotic Behavior
    Decay
    Dependent
    Zero

    Cite this

    @article{63e333997ac14fae923d4d1027cf059a,
    title = "Tail asymptotics for the bivariate skew normal",
    abstract = "We derive the asymptotic rate of decay to zero of the tail dependence of the bivariate skew normal distribution under the equal-skewness condition α1=α2, =α, say. The rate depends on whether α>0 or α<0. For the lower tail, the latter case has rate asymptotically identical with the bivariate normal (α=0), but has a different multiplicative constant. The case α>0 gives a rate dependent on α. The detailed asymptotic behaviour of the quantile function for the univariate skew normal is a key. This study is partly a sequel to our earlier one on the analogous situation for bivariate skew t.",
    author = "Thomas Fung and Eugene Seneta",
    year = "2016",
    month = "2",
    day = "1",
    doi = "10.1016/j.jmva.2015.11.002",
    language = "English",
    volume = "144",
    pages = "129--138",
    journal = "Journal of Multivariate Analysis",
    issn = "0047-259X",
    publisher = "Academic Press",

    }

    Tail asymptotics for the bivariate skew normal. / Fung, Thomas; Seneta, Eugene.

    In: Journal of Multivariate Analysis, Vol. 144, 01.02.2016, p. 129-138.

    Research output: Contribution to journalArticleResearchpeer-review

    TY - JOUR

    T1 - Tail asymptotics for the bivariate skew normal

    AU - Fung,Thomas

    AU - Seneta,Eugene

    PY - 2016/2/1

    Y1 - 2016/2/1

    N2 - We derive the asymptotic rate of decay to zero of the tail dependence of the bivariate skew normal distribution under the equal-skewness condition α1=α2, =α, say. The rate depends on whether α>0 or α<0. For the lower tail, the latter case has rate asymptotically identical with the bivariate normal (α=0), but has a different multiplicative constant. The case α>0 gives a rate dependent on α. The detailed asymptotic behaviour of the quantile function for the univariate skew normal is a key. This study is partly a sequel to our earlier one on the analogous situation for bivariate skew t.

    AB - We derive the asymptotic rate of decay to zero of the tail dependence of the bivariate skew normal distribution under the equal-skewness condition α1=α2, =α, say. The rate depends on whether α>0 or α<0. For the lower tail, the latter case has rate asymptotically identical with the bivariate normal (α=0), but has a different multiplicative constant. The case α>0 gives a rate dependent on α. The detailed asymptotic behaviour of the quantile function for the univariate skew normal is a key. This study is partly a sequel to our earlier one on the analogous situation for bivariate skew t.

    UR - http://www.scopus.com/inward/record.url?scp=84949231752&partnerID=8YFLogxK

    U2 - 10.1016/j.jmva.2015.11.002

    DO - 10.1016/j.jmva.2015.11.002

    M3 - Article

    VL - 144

    SP - 129

    EP - 138

    JO - Journal of Multivariate Analysis

    T2 - Journal of Multivariate Analysis

    JF - Journal of Multivariate Analysis

    SN - 0047-259X

    ER -