<?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 hal-02635566</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="2026-05-22T03:50:04+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">An ensemble learning method for variable selection: application to high dimensional data and missing values</title>
            <author role="aut">
              <persName>
                <forename type="first">Avner</forename>
                <surname>Bar-Hen</surname>
              </persName>
              <email type="md5">1246ab9543acd113a107a840f3970dd6</email>
              <email type="domain">cnam.fr</email>
              <idno type="idhal" notation="string">avner-bar-hen</idno>
              <idno type="idhal" notation="numeric">182343</idno>
              <idno type="halauthorid" notation="string">2743-182343</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-4449-8117</idno>
              <idno type="IDREF">https://www.idref.fr/103914579</idno>
              <affiliation ref="#struct-300351"/>
              <affiliation ref="#struct-390785"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Vincent</forename>
                <surname>Audigier</surname>
              </persName>
              <email type="md5">2a523d6346866903b32987714c2d79db</email>
              <email type="domain">cnam.fr</email>
              <idno type="idhal" notation="string">vincent-audigier</idno>
              <idno type="idhal" notation="numeric">182279</idno>
              <idno type="halauthorid" notation="string">53891-182279</idno>
              <idno type="ARXIV">https://arxiv.org/a/audigier_v_1</idno>
              <idno type="IDREF">https://www.idref.fr/146767519</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-4169-7866</idno>
              <orgName ref="#struct-108028"/>
              <affiliation ref="#struct-390785"/>
              <affiliation ref="#struct-300351"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Vincent</forename>
                <surname>Audigier</surname>
              </persName>
              <email type="md5">2a523d6346866903b32987714c2d79db</email>
              <email type="domain">cnam.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2020-06-18 14:13:33</date>
              <date type="whenModified">2025-07-09 15:06:18</date>
              <date type="whenReleased">2020-06-19 09:51:54</date>
              <date type="whenProduced">2022-04</date>
              <date type="whenEndEmbargoed">2020-06-18</date>
              <ref type="file" target="https://hal.science/hal-02635566v1/document">
                <date notBefore="2020-06-18"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-02635566v1/file/1808.06952.pdf" id="file-2873638-2526559">
                <date notBefore="2020-06-18"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/1808.06952"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="381054">
                <persName>
                  <forename>Vincent</forename>
                  <surname>Audigier</surname>
                </persName>
                <email type="md5">2a523d6346866903b32987714c2d79db</email>
                <email type="domain">cnam.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-02635566</idno>
            <idno type="halUri">https://hal.science/hal-02635566</idno>
            <idno type="halBibtex">barhen:hal-02635566</idno>
            <idno type="halRefHtml">&lt;i&gt;Journal of Statistical Computation and Simulation&lt;/i&gt;, 2022, &lt;a target="_blank" href="https://dx.doi.org/10.1080/00949655.2022.2070621"&gt;&amp;#x27E8;10.1080/00949655.2022.2070621&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Journal of Statistical Computation and Simulation, 2022, &amp;#x27E8;10.1080/00949655.2022.2070621&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-2873638-2526559"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNAM">Conservatoire National des Arts et Métiers</idno>
            <idno type="stamp" n="CEDRIC-CNAM" corresp="CNAM">Centre d'études et de recherche en informatique et communications </idno>
            <idno type="stamp" n="HESAM-CNAM" corresp="HESAM">Conservatoire National des Arts et Métiers - Hesam</idno>
            <idno type="stamp" n="HESAM">Hesam</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">An ensemble learning method for variable selection: application to high dimensional data and missing values</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Avner</forename>
                    <surname>Bar-Hen</surname>
                  </persName>
                  <email type="md5">1246ab9543acd113a107a840f3970dd6</email>
                  <email type="domain">cnam.fr</email>
                  <idno type="idhal" notation="string">avner-bar-hen</idno>
                  <idno type="idhal" notation="numeric">182343</idno>
                  <idno type="halauthorid" notation="string">2743-182343</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-4449-8117</idno>
                  <idno type="IDREF">https://www.idref.fr/103914579</idno>
                  <affiliation ref="#struct-300351"/>
                  <affiliation ref="#struct-390785"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Vincent</forename>
                    <surname>Audigier</surname>
                  </persName>
                  <email type="md5">2a523d6346866903b32987714c2d79db</email>
                  <email type="domain">cnam.fr</email>
                  <idno type="idhal" notation="string">vincent-audigier</idno>
                  <idno type="idhal" notation="numeric">182279</idno>
                  <idno type="halauthorid" notation="string">53891-182279</idno>
                  <idno type="ARXIV">https://arxiv.org/a/audigier_v_1</idno>
                  <idno type="IDREF">https://www.idref.fr/146767519</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-4169-7866</idno>
                  <orgName ref="#struct-108028"/>
                  <affiliation ref="#struct-390785"/>
                  <affiliation ref="#struct-300351"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">16249</idno>
                <idno type="issn">0094-9655</idno>
                <idno type="eissn">1563-5163</idno>
                <title level="j">Journal of Statistical Computation and Simulation</title>
                <imprint>
                  <publisher>Taylor &amp; Francis</publisher>
                  <date type="datePub">2022-04</date>
                  <date type="dateEpub">2022-05</date>
                </imprint>
              </monogr>
              <idno type="arxiv">1808.06952</idno>
              <idno type="doi">10.1080/00949655.2022.2070621</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Ensemble method</term>
                <term xml:lang="en">High Dimensional Data</term>
                <term xml:lang="en">Linear Regression</term>
              </keywords>
              <classCode scheme="halDomain" n="stat">Statistics [stat]</classCode>
              <classCode scheme="halDomain" n="stat.me">Statistics [stat]/Methodology [stat.ME]</classCode>
              <classCode scheme="halDomain" n="stat.ml">Statistics [stat]/Machine Learning [stat.ML]</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Standard approaches for variable selection in linear models are not tailored to deal properly with high-dimensional and incomplete data. Currently, methods dedicated to high-dimensional data handle missing values by ad hoc strategies, like complete case analysis or single imputation, while methods dedicated to missing values, mainly based on multiple imputation, do not discuss the imputation method to use with high-dimensional data. Consequently, both approaches appear to be limited for many modern applications. With inspiration from ensemble methods, a new variable selection method is proposed. It extends classical variable selection methods in the case of high-dimensional data with or without missing data. Theoretical properties are studied and the practical interest is demonstrated through a simulation study, as well as through an application to models specification in sequential multiple imputation. In the low-dimensional case, the procedure improves the control of the error risks, especially type I error, even without missing values for stepwise, lasso or knockoff methods. With missing values, the method performs better than reference selection methods based on multiple imputation. Similar performances are obtained in the high-dimensional case with or without missing values.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-300351" status="VALID">
          <idno type="IdRef">027404978</idno>
          <idno type="ISNI">0000000121690459</idno>
          <idno type="ROR">https://ror.org/0175hh227</idno>
          <orgName>Conservatoire National des Arts et Métiers [Cnam]</orgName>
          <orgName type="acronym">Cnam</orgName>
          <desc>
            <address>
              <addrLine>292 Rue Saint-Martin, 75003 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.cnam.fr/</ref>
          </desc>
        </org>
        <org type="researchteam" xml:id="struct-390785" status="VALID">
          <orgName>CEDRIC. Méthodes statistiques de data-mining et apprentissage</orgName>
          <orgName type="acronym">CEDRIC - MSDMA</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-16574" type="direct"/>
            <relation name="EA4629" active="#struct-179741" type="indirect"/>
            <relation name="EA4629" active="#struct-300351" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-16574" status="VALID">
          <idno type="IdRef">155463381</idno>
          <idno type="RNSR">201119480F</idno>
          <idno type="ROR">https://ror.org/044j5mm75</idno>
          <orgName>Centre d'études et de recherche en informatique et communications</orgName>
          <orgName type="acronym">CEDRIC</orgName>
          <desc>
            <address>
              <addrLine>292 rue Saint-Martin 75141 PARIS Cedex 03Case courrier 2D4P30</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://cedric.cnam.fr/</ref>
          </desc>
          <listRelation>
            <relation name="EA4629" active="#struct-179741" type="direct"/>
            <relation name="EA4629" active="#struct-300351" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-179741" status="VALID">
          <orgName>Ecole Nationale Supérieure d'Informatique pour l'Industrie et l'Entreprise</orgName>
          <orgName type="acronym">ENSIIE</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ensiie.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>