{"id":"https://openalex.org/W2141007997","doi":"https://doi.org/10.1186/1471-2105-7-91","title":"Bias in error estimation when using cross-validation for model selection","display_name":"Bias in error estimation when using cross-validation for model selection","publication_year":2006,"publication_date":"2006-02-23","ids":{"openalex":"https://openalex.org/W2141007997","doi":"https://doi.org/10.1186/1471-2105-7-91","mag":"2141007997","pmid":"https://pubmed.ncbi.nlm.nih.gov/16504092"},"language":"en","primary_location":{"id":"doi:10.1186/1471-2105-7-91","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-91","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-91","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","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-91","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004831674","display_name":"Sudhir Varma","orcid":"https://orcid.org/0000-0002-4096-4782"},"institutions":[{"id":"https://openalex.org/I4210140884","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210140884"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sudhir Varma","raw_affiliation_strings":["Biometric Research Branch, National Cancer Institute, Bethesda, MD, USA. varmas@mail.nih.gov","Biometric Research Branch, National Cancer Institute, Bethesda, USA"],"affiliations":[{"raw_affiliation_string":"Biometric Research Branch, National Cancer Institute, Bethesda, MD, USA. varmas@mail.nih.gov","institution_ids":["https://openalex.org/I4210140884"]},{"raw_affiliation_string":"Biometric Research Branch, National Cancer Institute, Bethesda, USA","institution_ids":["https://openalex.org/I4210140884"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101715307","display_name":"Richard Simon","orcid":"https://orcid.org/0000-0003-3558-4598"},"institutions":[{"id":"https://openalex.org/I4210140884","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210140884"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Simon","raw_affiliation_strings":["Biometric Research Branch, National Cancer Institute, Bethesda, MD, USA","Biometric Research Branch, National Cancer Institute, Bethesda, USA"],"affiliations":[{"raw_affiliation_string":"Biometric Research Branch, National Cancer Institute, Bethesda, MD, USA","institution_ids":["https://openalex.org/I4210140884"]},{"raw_affiliation_string":"Biometric Research Branch, National Cancer Institute, Bethesda, USA","institution_ids":["https://openalex.org/I4210140884"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5004831674"],"corresponding_institution_ids":["https://openalex.org/I4210140884"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":6.9472,"has_fulltext":true,"cited_by_count":1914,"citation_normalized_percentile":{"value":0.97777027,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"7","issue":"1","first_page":"91","last_page":"91"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9991000294685364,"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":0.9991000294685364,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9851999878883362,"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/classifier","display_name":"Classifier (UML)","score":0.7273218631744385},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6169459819793701},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6150842308998108},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.611228346824646},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.5368976593017578},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47912144660949707},{"id":"https://openalex.org/keywords/cross-validation","display_name":"Cross-validation","score":0.4724954664707184},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4616066515445709},{"id":"https://openalex.org/keywords/bayes-error-rate","display_name":"Bayes error rate","score":0.44150251150131226},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4294233024120331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4271978735923767},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34302380681037903},{"id":"https://openalex.org/keywords/bayes-classifier","display_name":"Bayes classifier","score":0.1232014000415802},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.09628209471702576}],"concepts":[{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.7273218631744385},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6169459819793701},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6150842308998108},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.611228346824646},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5368976593017578},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47912144660949707},{"id":"https://openalex.org/C27181475","wikidata":"https://www.wikidata.org/wiki/Q541014","display_name":"Cross-validation","level":2,"score":0.4724954664707184},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4616066515445709},{"id":"https://openalex.org/C143809311","wikidata":"https://www.wikidata.org/wiki/Q4874458","display_name":"Bayes error rate","level":5,"score":0.44150251150131226},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4294233024120331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4271978735923767},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34302380681037903},{"id":"https://openalex.org/C185207860","wikidata":"https://www.wikidata.org/wiki/Q17004744","display_name":"Bayes classifier","level":4,"score":0.1232014000415802},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.09628209471702576}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015982","descriptor_name":"Bias","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1186/1471-2105-7-91","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-91","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-91","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:16504092","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16504092","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:doaj.org/article:58c78fff8a39483d9f6f86fc889b4380","is_oa":true,"landing_page_url":"https://doaj.org/article/58c78fff8a39483d9f6f86fc889b4380","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 7, Iss 1, p 91 (2006)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:1397873","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/1397873","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"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"}],"best_oa_location":{"id":"doi:10.1186/1471-2105-7-91","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1471-2105-7-91","pdf_url":"https://bmcbioinformatics.biomedcentral.com/counter/pdf/10.1186/1471-2105-7-91","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":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2141007997.pdf","grobid_xml":"https://content.openalex.org/works/W2141007997.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W1978392040","https://openalex.org/W2043235003","https://openalex.org/W2105981176","https://openalex.org/W2107956883","https://openalex.org/W2126214330","https://openalex.org/W2127314075","https://openalex.org/W2135699773","https://openalex.org/W2138550913","https://openalex.org/W2148603752","https://openalex.org/W2153635508","https://openalex.org/W2167191085","https://openalex.org/W2799061466","https://openalex.org/W4243217231"],"related_works":["https://openalex.org/W2151191523","https://openalex.org/W115238348","https://openalex.org/W1973600295","https://openalex.org/W1599512561","https://openalex.org/W3143280635","https://openalex.org/W58702947","https://openalex.org/W4287244523","https://openalex.org/W2377040858","https://openalex.org/W2136903909","https://openalex.org/W2188630996"],"abstract_inverted_index":{"We":[0],"show":[1],"that":[2,13,47],"using":[3,18,41],"CV":[4,19,32,61,65],"to":[5],"compute":[6],"an":[7,68],"error":[8,36],"estimate":[9,24,71],"for":[10,33],"a":[11,21,38,42],"classifier":[12,39,54],"has":[14],"itself":[15],"been":[16],"tuned":[17],"gives":[20],"significantly":[22],"biased":[23],"of":[25,31,37,50,72],"the":[26,51,73],"true":[27,35,74],"error.":[28,75],"Proper":[29],"use":[30],"estimating":[34],"developed":[40],"well":[43],"defined":[44],"algorithm":[45],"requires":[46],"all":[48],"steps":[49],"algorithm,":[52],"including":[53],"parameter":[55],"tuning,":[56],"be":[57],"repeated":[58],"in":[59],"each":[60],"loop.":[62],"A":[63],"nested":[64],"procedure":[66],"provides":[67],"almost":[69],"unbiased":[70]},"counts_by_year":[{"year":2026,"cited_by_count":118},{"year":2025,"cited_by_count":246},{"year":2024,"cited_by_count":156},{"year":2023,"cited_by_count":179},{"year":2022,"cited_by_count":188},{"year":2021,"cited_by_count":190},{"year":2020,"cited_by_count":201},{"year":2019,"cited_by_count":121},{"year":2018,"cited_by_count":100},{"year":2017,"cited_by_count":90},{"year":2016,"cited_by_count":48},{"year":2015,"cited_by_count":48},{"year":2014,"cited_by_count":44},{"year":2013,"cited_by_count":42},{"year":2012,"cited_by_count":35}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}
