### Abstract

We examine the rate of decay to zero of the tail dependence coefficient ofthe bivariate skew t distribution which is obtained via normal variance-meanmixture in a case where there is no asymptotic tail dependence. Our resulthelps to explain the difference in performance in model fitting between thisskew t distribution and the one based on the variance mixing of the bivariateskew-normal distribution. This t distribution always displays asymptotictail dependence, as happens in the symmetric case which is common to bothmodels.

Original language | English |
---|---|

Pages (from-to) | 27-40 |

Number of pages | 14 |

Journal | Sri Lankan journal of applied statistics |

Volume | 12 |

Publication status | Published - 2011 |

Event | Statistical Concepts and Methods for the Modern World - Colombo, Sri Lanka Duration: 28 Dec 2011 → 30 Dec 2011 |

### Fingerprint

### Keywords

- asymptotic tail dependence
- regularly Varying Index
- skew t distributions
- tail behaviour