{"id":"https://openalex.org/W1875061881","doi":"https://doi.org/10.1186/1471-2105-8-25","title":"Bias in random forest variable importance measures: Illustrations, sources and a solution","display_name":"Bias in random forest variable importance measures: Illustrations, sources and a solution","publication_year":2007,"publication_date":"2007-01-25","ids":{"openalex":"https://openalex.org/W1875061881","doi":"https://doi.org/10.1186/1471-2105-8-25","mag":"1875061881","pmid":"https://pubmed.ncbi.nlm.nih.gov/17254353"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-8-25","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-8-25","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-8-25","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-8-25","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021387471","display_name":"Carolin Strobl","orcid":"https://orcid.org/0000-0003-0952-3230"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Carolin Strobl","raw_affiliation_strings":["Institut f\u00fcr Statistik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Ludwigstr, 33, 80539 M\u00fcnchen, Germany. carolin.strobl@stat.uni-muenchen.de","Institut f\u00fcr Statistik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Ludwigstr, 33, 80539 M\u00fcnchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Statistik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Ludwigstr, 33, 80539 M\u00fcnchen, Germany. carolin.strobl@stat.uni-muenchen.de","institution_ids":["https://openalex.org/I8204097"]},{"raw_affiliation_string":"Institut f\u00fcr Statistik, Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen, Ludwigstr, 33, 80539 M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015152016","display_name":"Anne\u2010Laure Boulesteix","orcid":"https://orcid.org/0000-0002-2729-0947"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anne-Laure Boulesteix","raw_affiliation_strings":["Institut f\u00fcr medizinische Statistik und Epidemiologie, Technische Universit\u00e4t M\u00fcnchen, Ismaningerstr. 22, 81675, M\u00fcnchen, Germany","Institut f\u00fcr Medizinische Statistik und Epidemiologie, Technische Universit\u00e4t M\u00fcnchen, M\u00fcnchen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr medizinische Statistik und Epidemiologie, Technische Universit\u00e4t M\u00fcnchen, Ismaningerstr. 22, 81675, M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Institut f\u00fcr Medizinische Statistik und Epidemiologie, Technische Universit\u00e4t M\u00fcnchen, M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014873408","display_name":"Achim Zeileis","orcid":"https://orcid.org/0000-0003-0918-3766"},"institutions":[{"id":"https://openalex.org/I102248843","display_name":"Vienna University of Economics and Business","ror":"https://ror.org/03yn8s215","country_code":"AT","type":"education","lineage":["https://openalex.org/I102248843"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Achim Zeileis","raw_affiliation_strings":["Department f\u00fcr Statistik und Mathematik, Wirtschaftsuniversit\u00e4t Wien, Augasse 2-6, 1090, Wien, Austria","Department f\u00fcr Statistik und Mathematik, Wirtschaftsuniversit\u00e4t Wien, Wien, Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department f\u00fcr Statistik und Mathematik, Wirtschaftsuniversit\u00e4t Wien, Augasse 2-6, 1090, Wien, Austria","institution_ids":["https://openalex.org/I102248843"]},{"raw_affiliation_string":"Department f\u00fcr Statistik und Mathematik, Wirtschaftsuniversit\u00e4t Wien, Wien, Austria","institution_ids":["https://openalex.org/I102248843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062348958","display_name":"Torsten Hothorn","orcid":"https://orcid.org/0000-0001-8301-0471"},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]},{"id":"https://openalex.org/I4210099379","display_name":"Zimmer Biomet (Germany)","ror":"https://ror.org/016731f38","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210099379","https://openalex.org/I4210115238"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Torsten Hothorn","raw_affiliation_strings":["Institut f\u00fcr Medizininformatik, Biometrie und Epidemiologie, Friedrich-Alexander-Universtit\u00e4t Erlangen-N\u00fcrnberg, Waldstr. 6, D-91054, Erlangen, Germany","Institut f\u00fcr Medizininformatik, Biometrie und Epidemiologie, Friedrich-Alexander-Universtit\u00e4t Erlangen-N\u00fcrnberg, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Medizininformatik, Biometrie und Epidemiologie, Friedrich-Alexander-Universtit\u00e4t Erlangen-N\u00fcrnberg, Waldstr. 6, D-91054, Erlangen, Germany","institution_ids":["https://openalex.org/I4210099379"]},{"raw_affiliation_string":"Institut f\u00fcr Medizininformatik, Biometrie und Epidemiologie, Friedrich-Alexander-Universtit\u00e4t Erlangen-N\u00fcrnberg, Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":16.8242,"has_fulltext":true,"cited_by_count":3598,"citation_normalized_percentile":{"value":0.99579952,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"8","issue":"1","first_page":"25","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.4717000126838684,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.4717000126838684,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.08720000088214874,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.034699998795986176,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.7935367822647095},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.7258830070495605},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.6386462450027466},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.573124349117279},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5295568108558655},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49378451704978943},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.463273286819458},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.44163185358047485},{"id":"https://openalex.org/keywords/variables","display_name":"Variables","score":0.43296271562576294},{"id":"https://openalex.org/keywords/instrumental-variable","display_name":"Instrumental variable","score":0.41540828347206116},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3760530352592468},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35474127531051636},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3209584951400757}],"concepts":[{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.7935367822647095},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7258830070495605},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.6386462450027466},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.573124349117279},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5295568108558655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49378451704978943},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.463273286819458},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.44163185358047485},{"id":"https://openalex.org/C27574286","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Variables","level":2,"score":0.43296271562576294},{"id":"https://openalex.org/C162144332","wikidata":"https://www.wikidata.org/wiki/Q1665305","display_name":"Instrumental variable","level":2,"score":0.41540828347206116},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3760530352592468},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35474127531051636},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3209584951400757},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003627","descriptor_name":"Data Interpretation, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008954","descriptor_name":"Models, Biological","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011157","descriptor_name":"Population Dynamics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011157","descriptor_name":"Population Dynamics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011157","descriptor_name":"Population Dynamics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":12,"locations":[{"id":"doi:10.1186/1471-2105-8-25","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-8-25","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-8-25","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:17254353","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/17254353","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:research.wu.ac.at:publications/0614d4e6-62c6-459b-8a7b-646ca0ef844f","is_oa":true,"landing_page_url":"https://research.wu.ac.at/de/publications/0614d4e6-62c6-459b-8a7b-646ca0ef844f","pdf_url":"https://research.wu.ac.at/ws/files/19792859/Strobl_etal_2007_BMC-Bioinformatics_Bias-in-random-forest-variable.pdf","source":{"id":"https://openalex.org/S7407055123","display_name":"WU Research","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Strobl, C, Boulesteix, A-L, Zeileis, A & Hothorn, T 2007, 'Bias in random forest variable importance measures: Illustrations, sources and a solution', BMC Bioinformatics, vol. 8, pp. 25. https://doi.org/10.1186/1471-2105-8-25","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:doi:10.5281/zenodo.13509995","is_oa":true,"landing_page_url":"https://zotero.org/groups/5435545/items/77ZV5KLY","pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"JournalArticle"},{"id":"pmh:oai:doaj.org/article:3a476a38ee3a45a7b9066bbc90d4b19a","is_oa":false,"landing_page_url":"https://doaj.org/article/3a476a38ee3a45a7b9066bbc90d4b19a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 8, Iss 1, p 25 (2007)","raw_type":"article"},{"id":"pmh:oai:econstor.eu:10419/31116","is_oa":false,"landing_page_url":"http://hdl.handle.net/10419/31116","pdf_url":null,"source":{"id":"https://openalex.org/S4306401696","display_name":"Econstor (Econstor)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:workingPaper"},{"id":"pmh:oai:epub.ub.uni-muenchen.de:1858","is_oa":false,"landing_page_url":"https://epub.ub.uni-muenchen.de/1858/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401845","display_name":"Open access LMU (Ludwid Maxmilian's Universitat Munchen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I8204097","host_organization_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","host_organization_lineage":["https://openalex.org/I8204097"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"doc-type:workingPaper"},{"id":"pmh:oai:epub.ub.uni-muenchen.de:23715","is_oa":false,"landing_page_url":"https://epub.ub.uni-muenchen.de/23715/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401845","display_name":"Open access LMU (Ludwid Maxmilian's Universitat Munchen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I8204097","host_organization_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","host_organization_lineage":["https://openalex.org/I8204097"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"doc-type:article"},{"id":"pmh:oai:epub.wu-wien.ac.at:4983","is_oa":false,"landing_page_url":"http://epub.wu.ac.at/4983/1/Strobl_etal_2007_BMC%2DBioinformatics_Bias%2Din%2Drandom%2Dforest%2Dvariable.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401630","display_name":"ePubWU Institutional Repository (Vienna University of Economics and Business)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I102248843","host_organization_name":"Vienna University of Economics and Business","host_organization_lineage":["https://openalex.org/I102248843"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:epub.wu-wien.ac.at:epub-wu-01_aaa","is_oa":false,"landing_page_url":"https://epub.wu.ac.at/1274/1/document.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400052","display_name":"ePubWU Institutional Repository (Wirtschaftsuniversit\u00e4t Wien)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Paper"},{"id":"pmh:oai:pubmedcentral.nih.gov:1796903","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1796903","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"doi:10.5282/ubm/epub.1858","is_oa":true,"landing_page_url":"https://doi.org/10.5282/ubm/epub.1858","pdf_url":null,"source":{"id":"https://openalex.org/S7407052039","display_name":"Universit\u00e4tsbibliothek der LMU","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-8-25","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-8-25","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-8-25","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land","score":0.75}],"awards":[{"id":"https://openalex.org/G4860333653","display_name":null,"funder_award_id":"HO 3242/1-3","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1875061881.pdf","grobid_xml":"https://content.openalex.org/works/W1875061881.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W149472151","https://openalex.org/W198570200","https://openalex.org/W273955616","https://openalex.org/W1481909093","https://openalex.org/W1496421042","https://openalex.org/W1520812622","https://openalex.org/W1539593569","https://openalex.org/W1594031697","https://openalex.org/W1641549771","https://openalex.org/W1678356000","https://openalex.org/W1849696878","https://openalex.org/W1978005360","https://openalex.org/W1986381824","https://openalex.org/W1988195734","https://openalex.org/W2033578818","https://openalex.org/W2040895371","https://openalex.org/W2043134049","https://openalex.org/W2061805653","https://openalex.org/W2068852101","https://openalex.org/W2072154218","https://openalex.org/W2086099578","https://openalex.org/W2097364929","https://openalex.org/W2106002880","https://openalex.org/W2110878112","https://openalex.org/W2112724659","https://openalex.org/W2119842880","https://openalex.org/W2123998733","https://openalex.org/W2133138357","https://openalex.org/W2159706865","https://openalex.org/W2169986380","https://openalex.org/W2187461225","https://openalex.org/W2204819850","https://openalex.org/W2335955811","https://openalex.org/W2582743722","https://openalex.org/W2607893089","https://openalex.org/W2911964244","https://openalex.org/W3026285062","https://openalex.org/W3085162807","https://openalex.org/W4231580960","https://openalex.org/W4244313837","https://openalex.org/W4249028376","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2051418878","https://openalex.org/W1594405807","https://openalex.org/W4388745254","https://openalex.org/W2980082554","https://openalex.org/W2767419625","https://openalex.org/W2389704471","https://openalex.org/W1517228774","https://openalex.org/W2117019857","https://openalex.org/W3022784071","https://openalex.org/W4251076796"],"abstract_inverted_index":{"BACKGROUND:":[0],"Variable":[1],"importance":[2,51,138,231,269],"measures":[3,52,139,232,270],"for":[4,28,38,57,101,237,275],"random":[5,48,135,181,207,263],"forests":[6],"have":[7],"been":[8],"receiving":[9],"increased":[10],"attention":[11],"as":[12,113],"a":[13,32,42,54,289],"means":[14,56],"of":[15,34,41,77,82,98,125,144,206,252,257,261],"variable":[16,50,58,137,160,170,212,230,238,268],"selection":[17,59,171,213,239],"in":[18,22,60,67,74,88,159,172,214,241,249,271,283,304],"many":[19,61],"classification":[20,175,217],"tasks":[21],"bioinformatics":[23,305],"and":[24,90,109,186,266,280],"related":[25],"scientific":[26],"fields,":[27],"instance":[29],"to":[30,178,201],"select":[31],"subset":[33],"genetic":[35],"markers":[36],"relevant":[37],"the":[39,147,173,180,195,215,228,244,272,295],"prediction":[40],"certain":[43],"disease.":[44],"We":[45,199],"show":[46,122],"that":[47,209],"forest":[49,136,182,264],"are":[53,64,130,140,149,168],"sensible":[55],"applications,":[62],"but":[63],"not":[65],"reliable":[66],"situations":[68,242],"where":[69,93,243],"potential":[70,245],"predictor":[71,153,246],"variables":[72,97,111,154,247],"vary":[73,248],"their":[75,80,250,255,267],"scale":[76,251],"measurement":[78,253],"or":[79,116,254],"number":[81,256],"categories.":[83,126,258],"This":[84],"is":[85,222,278],"particularly":[86],"important":[87],"genomics":[89],"computational":[91],"biology,":[92],"predictors":[94,104],"often":[95],"include":[96,105],"different":[99,123],"types,":[100,146],"example":[102],"when":[103,117,134],"both":[106,262],"sequence":[107,120],"data":[108,121,143,287],"continuous":[110],"such":[112],"folding":[114],"energy,":[115],"amino":[118],"acid":[119],"numbers":[124],"RESULTS:":[127],"Simulation":[128],"studies":[129],"presented":[131],"illustrating":[132],"that,":[133],"used":[141,177,235],"with":[142,192],"varying":[145],"results":[148],"misleading":[150],"because":[151],"suboptimal":[152],"may":[155],"be":[156,234,299],"artificially":[157],"preferred":[158],"selection.":[161],"The":[162,259],"two":[163],"mechanisms":[164],"underlying":[165],"this":[166,220],"deficiency":[167],"biased":[169],"individual":[174,216],"trees":[176],"build":[179],"on":[183,194,291],"one":[184],"hand,":[185],"effects":[187],"induced":[188],"by":[189,302],"bootstrap":[190],"sampling":[191],"replacement":[193],"other":[196],"hand.":[197],"CONCLUSION:":[198],"propose":[200],"employ":[202],"an":[203,284],"alternative":[204],"implementation":[205],"forests,":[208],"provides":[210],"unbiased":[211],"trees.":[218],"When":[219],"method":[221,297],"applied":[223,300],"using":[224],"subsampling":[225],"without":[226],"replacement,":[227],"resulting":[229],"can":[233,298],"reliably":[236],"even":[240],"usage":[260],"algorithms":[265],"R":[273],"system":[274],"statistical":[276],"computing":[277],"illustrated":[279],"documented":[281],"thoroughly":[282],"application":[285],"re-analyzing":[286],"from":[288],"study":[290],"RNA":[292],"editing.":[293],"Therefore":[294],"suggested":[296],"straightforwardly":[301],"scientists":[303],"research.":[306]},"counts_by_year":[{"year":2026,"cited_by_count":146},{"year":2025,"cited_by_count":301},{"year":2024,"cited_by_count":291},{"year":2023,"cited_by_count":367},{"year":2022,"cited_by_count":380},{"year":2021,"cited_by_count":427},{"year":2020,"cited_by_count":351},{"year":2019,"cited_by_count":248},{"year":2018,"cited_by_count":225},{"year":2017,"cited_by_count":151},{"year":2016,"cited_by_count":136},{"year":2015,"cited_by_count":126},{"year":2014,"cited_by_count":98},{"year":2013,"cited_by_count":84},{"year":2012,"cited_by_count":63}],"updated_date":"2026-06-12T08:23:45.883708","created_date":"2025-10-10T00:00:00"}