<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of inria-00310137</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-09T04:27:49+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Exact and Monte Carlo Calculations of Integrated Likelihoods for the Latent Class Model</title>
            <author role="aut">
              <persName>
                <forename type="first">Christophe</forename>
                <surname>Biernacki</surname>
              </persName>
              <idno type="halauthorid">142378-0</idno>
              <affiliation ref="#struct-32"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Gilles</forename>
                <surname>Celeux</surname>
              </persName>
              <email type="md5">df100d9b40871a647a8da156d97ddbc3</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="numeric">833415</idno>
              <idno type="halauthorid" notation="string">142379-833415</idno>
              <idno type="IDREF">https://www.idref.fr/02951598X</idno>
              <idno type="VIAF">https://viaf.org/viaf/56641197</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7221-6594</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=dl3nPvwAAAAJ</idno>
              <affiliation ref="#struct-56055"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Gérard</forename>
                <surname>Govaert</surname>
              </persName>
              <email type="md5">9172ccaa4a0c29fa4665e132a7ffea1f</email>
              <email type="domain">utc.fr</email>
              <idno type="idhal" notation="string">gerard-govaert</idno>
              <idno type="idhal" notation="numeric">7762</idno>
              <idno type="halauthorid" notation="string">2105-7762</idno>
              <idno type="IDREF">https://www.idref.fr/059389710</idno>
              <affiliation ref="#struct-389870"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Gilles</forename>
                <surname>Celeux</surname>
              </persName>
              <email type="md5">df100d9b40871a647a8da156d97ddbc3</email>
              <email type="domain">inria.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2008-08-07 18:45:12</date>
              <date type="whenWritten">2008</date>
              <date type="whenModified">2025-06-24 10:16:03</date>
              <date type="whenReleased">2008-08-07 22:00:26</date>
              <date type="whenProduced">2008</date>
              <date type="whenEndEmbargoed">2008-08-07</date>
              <ref type="file" target="https://inria.hal.science/inria-00310137v1/document">
                <date notBefore="2008-08-07"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/inria-00310137v1/file/RR6609.pdf" id="file-310137-47079">
                <date notBefore="2008-08-07"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="111544">
                <persName>
                  <forename>Gilles</forename>
                  <surname>Celeux</surname>
                </persName>
                <email type="md5">df100d9b40871a647a8da156d97ddbc3</email>
                <email type="domain">inria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">inria-00310137</idno>
            <idno type="halUri">https://inria.hal.science/inria-00310137</idno>
            <idno type="halBibtex">biernacki:inria-00310137</idno>
            <idno type="halRefHtml">[Research Report] RR-6609, INRIA. 2008, pp.25</idno>
            <idno type="halRef">[Research Report] RR-6609, INRIA. 2008, pp.25</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-310137-47079"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="UNIV-COMPIEGNE">Université de Technologie de Compiègne</idno>
            <idno type="stamp" n="UNIV-PSUD">Université Paris Sud - Paris XI</idno>
            <idno type="stamp" n="INRIA-RRRT">Rapports de recherche et Technique de l'Inria</idno>
            <idno type="stamp" n="INRIA-SACLAY" corresp="INRIA">INRIA Saclay - Ile de France</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="LORIA2">Publications du LORIA</idno>
            <idno type="stamp" n="LM-ORSAY">Laboratoire de Mathématiques d'Orsay</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="HEUDIASYC" corresp="UNIV-COMPIEGNE">Laboratoire HEUDIASYC - Heuristique et Diagnostic des Systèmes Complexes</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="LARA">LARA</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="UNIV-PSUD-SACLAY" corresp="UNIV-PARIS-SACLAY">Université Paris Sud pour Paris Saclay</idno>
            <idno type="stamp" n="UNIV-LILLE">Université de Lille</idno>
            <idno type="stamp" n="GS-MATHEMATIQUES">Graduate School Mathématiques</idno>
            <idno type="stamp" n="ALLIANCE-SU"> Alliance Sorbonne Université</idno>
            <idno type="stamp" n="LPP-MATH">Laboratoire Paul Painlevé (UMR8524)</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="1">Not set</note>
            <note type="report" n="6">Research Report</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Exact and Monte Carlo Calculations of Integrated Likelihoods for the Latent Class Model</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Christophe</forename>
                    <surname>Biernacki</surname>
                  </persName>
                  <idno type="halauthorid">142378-0</idno>
                  <affiliation ref="#struct-32"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Gilles</forename>
                    <surname>Celeux</surname>
                  </persName>
                  <email type="md5">df100d9b40871a647a8da156d97ddbc3</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="numeric">833415</idno>
                  <idno type="halauthorid" notation="string">142379-833415</idno>
                  <idno type="IDREF">https://www.idref.fr/02951598X</idno>
                  <idno type="VIAF">https://viaf.org/viaf/56641197</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7221-6594</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=dl3nPvwAAAAJ</idno>
                  <affiliation ref="#struct-56055"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Gérard</forename>
                    <surname>Govaert</surname>
                  </persName>
                  <email type="md5">9172ccaa4a0c29fa4665e132a7ffea1f</email>
                  <email type="domain">utc.fr</email>
                  <idno type="idhal" notation="string">gerard-govaert</idno>
                  <idno type="idhal" notation="numeric">7762</idno>
                  <idno type="halauthorid" notation="string">2105-7762</idno>
                  <idno type="IDREF">https://www.idref.fr/059389710</idno>
                  <affiliation ref="#struct-389870"/>
                </author>
              </analytic>
              <monogr>
                <idno type="reportNumber">RR-6609</idno>
                <imprint>
                  <biblScope unit="pp">25</biblScope>
                  <date type="datePub">2008</date>
                </imprint>
                <authority type="institution">INRIA</authority>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Categorical data</term>
                <term xml:lang="en">Bayesian model selection</term>
                <term xml:lang="en">Jeffreys conjugate prior</term>
                <term xml:lang="en">importance sampling</term>
                <term xml:lang="en">EM algorithm</term>
                <term xml:lang="en">Gibbs sampler</term>
              </keywords>
              <classCode scheme="halDomain" n="math.math-st">Mathematics [math]/Statistics [math.ST]</classCode>
              <classCode scheme="halDomain" n="stat.th">Statistics [stat]/Statistics Theory [stat.TH]</classCode>
              <classCode scheme="halTypology" n="REPORT">Reports</classCode>
              <classCode scheme="halOldTypology" n="REPORT">Reports</classCode>
              <classCode scheme="halTreeTypology" n="REPORT.RESREPORT">Reports - Research report</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>The latent class model or multivariate multinomial mixture is a powerful approach for clustering categorical data. This model uses a conditional independence assumption given the latent class to which an object is belonging to represent heterogeneous populations. . In this paper, we exploit the fact that a fully Bayesian analysis with Jeffreys non informative prior distributions does not involve technical difficulty to propose an exact expression of the integrated {\em complete-data} likelihood, which is known as being a meaningful model selection criterion in a clustering perspective. Similarly, a Monte Carlo approximation of the integrated {\em observed-data} likelihood can be obtained in two steps: An exact integration over the parameters is followed by an approximation of the sum over all possible partitions through either a frequentist or a Bayesian importance sampling strategy. Then, the exact and the approximate criteria experimentally compete respectively with their standard asymptotic BIC approximations for choosing the number of mixture components. Numerical experiments on simulated data and a biological example highlight that asymptotic criteria are usually dramatically more conservative than the non asymptotic presented criteria, not only for moderate sample sizes as expected but also for quite large sample sizes. It appears that asymptotic standard criteria could often fail to select some interesting structures present in the data. It is also the opportunity to highlight the deep purpose difference between the integrated {\em complete-data} and the {\em observed-data} likelihoods: The integrated {\em complete-data} likelihood is focussing on a cluster analysis view and favors well separated clusters, implying some robustness against model misspecification, while the integrated {\em observed-data} likelihood is focussing on a density estimation view and is expected to provide a consistent estimation of the distribution of the data.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-32" status="VALID">
          <idno type="IdRef">161603971</idno>
          <idno type="ISNI">0000000403684081</idno>
          <idno type="RNSR">199812852H</idno>
          <idno type="ROR">https://ror.org/043n4fm24</idno>
          <idno type="Wikidata">Q3214464</idno>
          <orgName>Laboratoire Paul Painlevé - UMR 8524</orgName>
          <orgName type="acronym">LPP</orgName>
          <date type="start">2004-01-01</date>
          <desc>
            <address>
              <addrLine>Université de Lille - Sciences et technologies - U.F.R. de Mathématiques - 59655 Villeneuve d'Ascq Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://math.univ-lille.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UMR8524" active="#struct-374570" type="direct"/>
            <relation name="UMR8524" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-56055" status="OLD">
          <idno type="RNSR">200718365L</idno>
          <orgName>Model selection in statistical learning</orgName>
          <orgName type="acronym">SELECT</orgName>
          <date type="start">2007-01-01</date>
          <date type="end">2018-12-31</date>
          <desc>
            <address>
              <addrLine>1 rue Honoré d'Estienne d'Orves 91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/select</ref>
          </desc>
          <listRelation>
            <relation active="#struct-40" type="direct"/>
            <relation active="#struct-92966" type="indirect"/>
            <relation name="UMR8628" active="#struct-441569" type="indirect"/>
            <relation active="#struct-118511" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-389870" status="VALID">
          <idno type="IdRef">110410807</idno>
          <idno type="ISNI">0000 0004 0452 2471</idno>
          <idno type="RNSR">201220263C</idno>
          <idno type="ROR">https://ror.org/0075hvk77</idno>
          <orgName>Heuristique et Diagnostic des Systèmes Complexes [Compiègne]</orgName>
          <orgName type="acronym">Heudiasyc</orgName>
          <desc>
            <address>
              <addrLine>UTC, CS 60319 - 57 avenue de Landshut - 60203 Compiègne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.hds.utc.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-93027" type="direct"/>
            <relation name="UMR7253" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-374570" status="VALID">
          <idno type="IdRef">223446556</idno>
          <idno type="ISNI">0000 0001 2242 6780</idno>
          <idno type="ROR">https://ror.org/02kzqn938</idno>
          <idno type="Wikidata">Q3551621</idno>
          <orgName>Université de Lille</orgName>
          <desc>
            <address>
              <addrLine>EPE Université de Lille. -- 42 rue Paul Duez, 59000 Lille</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-lille.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-40" status="OLD">
          <orgName>Laboratoire de Mathématiques d'Orsay</orgName>
          <orgName type="acronym">LMO</orgName>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>Bâtiment 307, rue Michel Magat, Faculté des sciences, Université Paris-Saclay, 91405 Orsay Cédex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.math.u-psud.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-92966" type="direct"/>
            <relation name="UMR8628" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-92966" status="OLD">
          <idno type="ROR">https://ror.org/028rypz17</idno>
          <orgName>Université Paris-Sud - Paris 11</orgName>
          <orgName type="acronym">UP11</orgName>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>Bâtiment 300 - 91405 Orsay cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.u-psud.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-118511" status="VALID">
          <idno type="RNSR">200818248E</idno>
          <idno type="ROR">https://ror.org/0315e5x55</idno>
          <orgName>Centre Inria de Saclay</orgName>
          <desc>
            <address>
              <addrLine>1 rue Honoré d'Estienne d'OrvesBâtiment Alan TuringCampus de l'École Polytechnique91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/saclay</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300009" status="VALID">
          <idno type="ROR">https://ror.org/02kvxyf05</idno>
          <orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
          <orgName type="acronym">Inria</orgName>
          <desc>
            <address>
              <addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/en/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-93027" status="VALID">
          <idno type="ROR">https://ror.org/04y5kwa70</idno>
          <orgName>Université de Technologie de Compiègne</orgName>
          <orgName type="acronym">UTC</orgName>
          <desc>
            <address>
              <addrLine>Université de Technologie de Compiègne - rue du Docteur Schweitzer- CS 60319 - 60203 Compiègne Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.utc.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>