Robust estimates of insurance misrepresentation through kernel quantile regression mixtures

<?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">MAP20210028137</controlfield>
    <controlfield tag="003">MAP</controlfield>
    <controlfield tag="005">20220911211005.0</controlfield>
    <controlfield tag="008">210929e2021    esp|||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">21</subfield>
    </datafield>
    <datafield tag="100" ind1=" " ind2=" ">
      <subfield code="0">MAPA20170005766</subfield>
      <subfield code="a">Li, Hong</subfield>
    </datafield>
    <datafield tag="245" ind1="1" ind2="0">
      <subfield code="a">Robust estimates of insurance misrepresentation through kernel quantile regression mixtures</subfield>
      <subfield code="c">Hong Li, Qifan Song, Jianxi Su</subfield>
    </datafield>
    <datafield tag="520" ind1=" " ind2=" ">
      <subfield code="a">This paper pertains to a class of nonparametric methods for studying the misrepresentation issue in insurance applications. For this purpose, mixture models based on quantile regression in reproducing kernel Hilbert spaces are employed. Compared with the existing parametric approaches, the proposed framework features a more flexible statistics structure which could alleviate the risk of model misspecification, and is in the meantime more robust to outliers in the data. The proposed framework can not only estimate the prevalence of misrepresentation in the data, but also help identify the most suspicious individuals for the validation purpose. Through embedding state-of-the-art machine learning techniques, we present a novel statistics procedure to efficiently estimate the proposed misrepresentation model in the presence of massive data. The proposed methodology is applied to study the Medical Expenditure Panel Survey data, and a significant degree of misrepresentation activity is found on the self-reported insurance status.</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080590567</subfield>
      <subfield code="a">Empresas de seguros</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080586294</subfield>
      <subfield code="a">Mercado de seguros</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080586546</subfield>
      <subfield code="a">Nuevas tecnologías</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20140022717</subfield>
      <subfield code="a">Big data</subfield>
    </datafield>
    <datafield tag="700" ind1="1" ind2=" ">
      <subfield code="0">MAPA20210032844</subfield>
      <subfield code="a">Song, Qifan</subfield>
    </datafield>
    <datafield tag="700" ind1="1" ind2=" ">
      <subfield code="0">MAPA20170002697</subfield>
      <subfield code="a">Su, Jianxi</subfield>
    </datafield>
    <datafield tag="773" ind1="0" ind2=" ">
      <subfield code="w">MAP20077000727</subfield>
      <subfield code="t">The Journal of risk and insurance</subfield>
      <subfield code="d">Nueva York : The American Risk and Insurance Association, 1964-</subfield>
      <subfield code="x">0022-4367</subfield>
      <subfield code="g">01/09/2021 Volumen 88 Número 3 - septiembre 2021 , p. 625-663</subfield>
    </datafield>
    <datafield tag="856" ind1=" " ind2=" ">
      <subfield code="y">MÁS INFORMACIÓN</subfield>
      <subfield code="u">mailto:centrodocumentacion@fundacionmapfre.org?subject=Consulta%20de%20una%20publicaci%C3%B3n%20&body=Necesito%20m%C3%A1s%20informaci%C3%B3n%20sobre%20este%20documento%3A%0A%0A%5Banote%20el%20titulo%20completo%20del%20documento%20del%20que%20desea%20informaci%C3%B3n%5D%0A%0AGracias</subfield>
    </datafield>
  </record>
</collection>