{"id":"https://openalex.org/W2008769248","doi":"https://doi.org/10.1162/089976603321891864","title":"Comparison of Model Selection for Regression","display_name":"Comparison of Model Selection for Regression","publication_year":2003,"publication_date":"2003-06-03","ids":{"openalex":"https://openalex.org/W2008769248","doi":"https://doi.org/10.1162/089976603321891864","mag":"2008769248","pmid":"https://pubmed.ncbi.nlm.nih.gov/12816572"},"language":"en","primary_location":{"id":"doi:10.1162/089976603321891864","is_oa":false,"landing_page_url":"https://doi.org/10.1162/089976603321891864","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051555620","display_name":"Vladimir Cherkassky","orcid":null},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vladimir Cherkassky","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN 55455, U.S.A.,"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN 55455, U.S.A.,","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025885659","display_name":"Yunqian Ma","orcid":"https://orcid.org/0000-0002-8531-5989"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunqian Ma","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN 55455, U.S.A.,"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, MN 55455, U.S.A.,","institution_ids":["https://openalex.org/I130238516"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051555620"],"corresponding_institution_ids":["https://openalex.org/I130238516"],"apc_list":null,"apc_paid":null,"fwci":5.2817,"has_fulltext":false,"cited_by_count":146,"citation_normalized_percentile":{"value":0.9601147,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"15","issue":"7","first_page":"1691","last_page":"1714"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11871","display_name":"Advanced Statistical Methods and Models","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11871","display_name":"Advanced Statistical Methods and Models","score":0.9994999766349792,"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/T10136","display_name":"Statistical Methods and Inference","score":0.9968000054359436,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9930999875068665,"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/akaike-information-criterion","display_name":"Akaike information criterion","score":0.8047435879707336},{"id":"https://openalex.org/keywords/bayesian-information-criterion","display_name":"Bayesian information criterion","score":0.7542601227760315},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6786078214645386},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.6395679116249084},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4948415160179138},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4847957193851471},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.44697579741477966},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.4281757175922394},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.4241429269313812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33887171745300293},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33736321330070496},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3157520294189453}],"concepts":[{"id":"https://openalex.org/C126674687","wikidata":"https://www.wikidata.org/wiki/Q1662573","display_name":"Akaike information criterion","level":2,"score":0.8047435879707336},{"id":"https://openalex.org/C168136583","wikidata":"https://www.wikidata.org/wiki/Q1988242","display_name":"Bayesian information criterion","level":2,"score":0.7542601227760315},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6786078214645386},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.6395679116249084},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4948415160179138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4847957193851471},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.44697579741477966},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.4281757175922394},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4241429269313812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33887171745300293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33736321330070496},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3157520294189453}],"mesh":[{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012044","descriptor_name":"Regression Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012044","descriptor_name":"Regression Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012044","descriptor_name":"Regression Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1162/089976603321891864","is_oa":false,"landing_page_url":"https://doi.org/10.1162/089976603321891864","pdf_url":null,"source":{"id":"https://openalex.org/S207023548","display_name":"Neural Computation","issn_l":"0899-7667","issn":["0899-7667","1530-888X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computation","raw_type":"journal-article"},{"id":"pmid:12816572","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12816572","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":"Neural computation","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320315254","display_name":"Innovative Research Group Project of the National Natural Science Foundation of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1506281249","https://openalex.org/W1553407966","https://openalex.org/W1554663460","https://openalex.org/W1554944419","https://openalex.org/W1591760165","https://openalex.org/W1998255116","https://openalex.org/W2000939693","https://openalex.org/W2061317273","https://openalex.org/W2069888879","https://openalex.org/W2105400096","https://openalex.org/W2117812871","https://openalex.org/W2120433189","https://openalex.org/W2142635246","https://openalex.org/W2148603752","https://openalex.org/W2156909104","https://openalex.org/W2158994553","https://openalex.org/W2163349744","https://openalex.org/W2169502938","https://openalex.org/W4243797702"],"related_works":["https://openalex.org/W3122388856","https://openalex.org/W2509820422","https://openalex.org/W2033907215","https://openalex.org/W2963415778","https://openalex.org/W2114625140","https://openalex.org/W2783425804","https://openalex.org/W1502087262","https://openalex.org/W2963176572","https://openalex.org/W1968886786","https://openalex.org/W304661108"],"abstract_inverted_index":{"We":[0,193],"discuss":[1,180],"empirical":[2,34,71,101,151,207],"comparison":[3],"of":[4,28,110,125,175,190,199,202,215],"analytical":[5],"methods":[6,39,143],"for":[7,19,24,63,87,103,133,184,206,218],"model":[8,88,127,203,216],"selection.":[9],"Currently,":[10],"there":[11],"is":[12,68,158],"no":[13],"consensus":[14],"on":[15,59],"the":[16,25,52,82,122,155,197],"best":[17],"method":[18,84],"finite-sample":[20],"estimation":[21,201],"problems,":[22],"even":[23],"simple":[26],"case":[27],"linear":[29],"estimators.":[30],"This":[31,148],"article":[32],"presents":[33],"comparisons":[35,72,102,186,208],"between":[36],"classical":[37],"statistical":[38],"-":[40,50],"Akaike":[41],"information":[42,47],"criterion":[43,48],"(AIC)":[44],"and":[45,51,76,90,107,115,141,173,187,209],"Bayesian":[46],"(BIC)":[49],"structural":[53],"risk":[54],"minimization":[55],"(SRM)":[56],"method,":[57],"based":[58],"Vapnik-Chervonenkis":[60],"(VC)":[61],"theory,":[62],"regression":[64],"problems.":[65],"Our":[66,119],"study":[67],"motivated":[69],"by":[70,160],"in":[73,163,169],"Hastie,":[74],"Tibshirani,":[75],"Friedman":[77],"(2001),":[78,167],"which":[79],"claims":[80],"that":[81,92],"SRM":[83,140,176,191],"performs":[85],"poorly":[86],"selection":[89],"suggests":[91],"AIC":[93,132],"yields":[94],"superior":[95],"predictive":[96,146],"performance.":[97,147],"Hence,":[98,178],"we":[99,179],"present":[100],"various":[104],"data":[105,135],"sets":[106],"different":[108],"types":[109],"estimators":[111],"(linear,":[112],"subset":[113],"selection,":[114],"k-nearest":[116,219],"neighbor":[117],"regression).":[118],"results":[120,152],"demonstrate":[121],"practical":[123,188,213],"advantages":[124],"VC-based":[126],"selection;":[128],"it":[129],"consistently":[130],"outperforms":[131],"all":[134],"sets.":[136],"In":[137],"our":[138],"study,":[139],"BIC":[142],"show":[144],"similar":[145],"discrepancy":[149],"(between":[150],"obtained":[153],"using":[154],"same":[156],"data)":[157],"caused":[159],"methodological":[161,181],"drawbacks":[162],"Hastie":[164],"et":[165],"al.":[166],"especially":[168],"their":[170],"loose":[171],"interpretation":[172],"application":[174,189],"method.":[177,192],"issues":[182],"important":[183],"meaningful":[185],"also":[194],"point":[195],"out":[196],"importance":[198],"accurate":[200],"complexity":[204,217],"(VC-dimension)":[205],"propose":[210],"a":[211],"new":[212],"estimate":[214],"neighbors":[220],"regression.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}