Modified Gaussian pseudo-copula : applications in insurance and finance

<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.loc.gov/MARC21/slim http://www.loc.gov/standards/marcxml/schema/MARC21slim.xsd">
  <record>
    <leader>00000cab a2200000   4500</leader>
    <controlfield tag="001">MAP20130027210</controlfield>
    <controlfield tag="003">MAP</controlfield>
    <controlfield tag="005">20130920151457.0</controlfield>
    <controlfield tag="008">130905e20130701esp|||p      |0|||b|spa d</controlfield>
    <datafield tag="040" ind1=" " ind2=" ">
      <subfield code="a">MAP</subfield>
      <subfield code="b">spa</subfield>
      <subfield code="d">MAP</subfield>
    </datafield>
    <datafield tag="084" ind1=" " ind2=" ">
      <subfield code="a">6</subfield>
    </datafield>
    <datafield tag="100" ind1="1" ind2=" ">
      <subfield code="0">MAPA20130011684</subfield>
      <subfield code="a">Fang, Y.</subfield>
    </datafield>
    <datafield tag="245" ind1="1" ind2="0">
      <subfield code="a">Modified Gaussian pseudo-copula</subfield>
      <subfield code="b">: applications in insurance and finance</subfield>
      <subfield code="c">Y. Fang, L. Madsen</subfield>
    </datafield>
    <datafield tag="520" ind1=" " ind2=" ">
      <subfield code="a">The Gaussian copula is by far the most popular copula for modeling the association in finance and insurance risk problems. However, one major drawback of Gaussian copula is that it intrinsically lacks the flexibility of modeling the tail dependence, which real life data often exhibit. In this paper, we present the modified Gaussian copula, a pseudo-copula model that allows for both tail dependence and elliptical dependence structure. To improve model flexibility, the Gaussian copula is modified such that each correlation coefficient is not only an unknown parameter (to be modeled), but also a function of random variables. We present the characteristics of the modified Gaussian pseudo-copula and show that our modification enables the copula to capture the tail dependence adequately. The proposed modified Gaussian pseudo-copula is assessed by estimating the association on a real life insurance data and a finance data set. Furthermore, a comprehensive simulation study comparing goodness-of-fit test statistics is carried out. Both experiment results demonstrate that our Modified Gaussian pseudo-copula fits data (with or without tail dependence) generally better than other common copulas</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080576790</subfield>
      <subfield code="a">Modelo Gaussiano</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080602437</subfield>
      <subfield code="a">Matemática del seguro</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20090035034</subfield>
      <subfield code="a">Modelización mediante cópulas</subfield>
    </datafield>
    <datafield tag="700" ind1="1" ind2=" ">
      <subfield code="0">MAPA20130012582</subfield>
      <subfield code="a">Madsen, L.</subfield>
    </datafield>
    <datafield tag="773" ind1="0" ind2=" ">
      <subfield code="w">MAP20077100574</subfield>
      <subfield code="t">Insurance : mathematics and economics</subfield>
      <subfield code="d">Oxford : Elsevier, 1990-</subfield>
      <subfield code="x">0167-6687</subfield>
      <subfield code="g">01/07/2013 Volumen 53 Número 1 - julio 2013 , p. 292-301</subfield>
    </datafield>
  </record>
</collection>