{"id":"https://openalex.org/W4399580180","doi":"https://doi.org/10.1007/s11222-024-10442-4","title":"Efficient estimation and correction of selection-induced bias with order statistics","display_name":"Efficient estimation and correction of selection-induced bias with order statistics","publication_year":2024,"publication_date":"2024-06-12","ids":{"openalex":"https://openalex.org/W4399580180","doi":"https://doi.org/10.1007/s11222-024-10442-4"},"language":"en","primary_location":{"id":"doi:10.1007/s11222-024-10442-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11222-024-10442-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11222-024-10442-4.pdf","source":{"id":"https://openalex.org/S5437875","display_name":"Statistics and Computing","issn_l":"0960-3174","issn":["0960-3174","1573-1375"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","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":"Statistics and Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11222-024-10442-4.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060057041","display_name":"Yann McLatchie","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Yann McLatchie","raw_affiliation_strings":["Department of Computer Science, Aalto University, Espoo, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047269552","display_name":"Aki Vehtari","orcid":"https://orcid.org/0000-0003-2164-9469"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Aki Vehtari","raw_affiliation_strings":["Department of Computer Science, Aalto University, Espoo, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5060057041"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":{"value":2090,"currency":"EUR","value_usd":2690},"apc_paid":{"value":2090,"currency":"EUR","value_usd":2690},"fwci":2.2964,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.88798954,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"34","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10928","display_name":"Probabilistic and Robust Engineering Design","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10928","display_name":"Probabilistic and Robust Engineering Design","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.9979000091552734,"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/T11235","display_name":"Statistical Methods in Clinical Trials","score":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.7038511037826538},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6744151711463928},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.6650486588478088},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5361788868904114},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.531489372253418},{"id":"https://openalex.org/keywords/selection-bias","display_name":"Selection bias","score":0.5252475142478943},{"id":"https://openalex.org/keywords/statistician","display_name":"Statistician","score":0.5010273456573486},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4675741493701935},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42500150203704834},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4222421944141388},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.37902212142944336},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3621451258659363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34261536598205566},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.31215232610702515},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19026988744735718}],"concepts":[{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.7038511037826538},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6744151711463928},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.6650486588478088},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5361788868904114},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.531489372253418},{"id":"https://openalex.org/C40423286","wikidata":"https://www.wikidata.org/wiki/Q284172","display_name":"Selection bias","level":2,"score":0.5252475142478943},{"id":"https://openalex.org/C2779677306","wikidata":"https://www.wikidata.org/wiki/Q2732142","display_name":"Statistician","level":2,"score":0.5010273456573486},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4675741493701935},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42500150203704834},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4222421944141388},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.37902212142944336},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3621451258659363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34261536598205566},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.31215232610702515},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19026988744735718},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11222-024-10442-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11222-024-10442-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11222-024-10442-4.pdf","source":{"id":"https://openalex.org/S5437875","display_name":"Statistics and Computing","issn_l":"0960-3174","issn":["0960-3174","1573-1375"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","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":"Statistics and Computing","raw_type":"journal-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/129394","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/80766119-1e9e-4775-9554-3344797e8627","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"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":null,"raw_type":"publishedVersion"}],"best_oa_location":{"id":"doi:10.1007/s11222-024-10442-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11222-024-10442-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11222-024-10442-4.pdf","source":{"id":"https://openalex.org/S5437875","display_name":"Statistics and Computing","issn_l":"0960-3174","issn":["0960-3174","1573-1375"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","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":"Statistics and Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321394","display_name":"Aalto-Yliopisto","ror":"https://ror.org/020hwjq30"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4399580180.pdf"},"referenced_works_count":67,"referenced_works":["https://openalex.org/W142046526","https://openalex.org/W1603903339","https://openalex.org/W1877880381","https://openalex.org/W1960471525","https://openalex.org/W1963735520","https://openalex.org/W1967294304","https://openalex.org/W1967396577","https://openalex.org/W1974315578","https://openalex.org/W1976990135","https://openalex.org/W1981251392","https://openalex.org/W1981299323","https://openalex.org/W1981552604","https://openalex.org/W1986672307","https://openalex.org/W1987223022","https://openalex.org/W1997924543","https://openalex.org/W2007069447","https://openalex.org/W2009435671","https://openalex.org/W2016219233","https://openalex.org/W2020599875","https://openalex.org/W2029199047","https://openalex.org/W2033872649","https://openalex.org/W2035035907","https://openalex.org/W2057765075","https://openalex.org/W2073610283","https://openalex.org/W2080951248","https://openalex.org/W2105090664","https://openalex.org/W2107956883","https://openalex.org/W2108868276","https://openalex.org/W2112081648","https://openalex.org/W2127874106","https://openalex.org/W2130902307","https://openalex.org/W2146934839","https://openalex.org/W2159347337","https://openalex.org/W2160300619","https://openalex.org/W2160624840","https://openalex.org/W2203714058","https://openalex.org/W2265882717","https://openalex.org/W2471967545","https://openalex.org/W2479236352","https://openalex.org/W2731461838","https://openalex.org/W2747622113","https://openalex.org/W2894867725","https://openalex.org/W2911352402","https://openalex.org/W2951464221","https://openalex.org/W3024653609","https://openalex.org/W3088522645","https://openalex.org/W3102024356","https://openalex.org/W3102737393","https://openalex.org/W3102763196","https://openalex.org/W3104312965","https://openalex.org/W3104887532","https://openalex.org/W3105620286","https://openalex.org/W3123421154","https://openalex.org/W3175417087","https://openalex.org/W3182438885","https://openalex.org/W3203735501","https://openalex.org/W3217742050","https://openalex.org/W4207040139","https://openalex.org/W4211177544","https://openalex.org/W4232632925","https://openalex.org/W4248681815","https://openalex.org/W4251028892","https://openalex.org/W4382724518","https://openalex.org/W4388319582","https://openalex.org/W4390886690","https://openalex.org/W4399138311","https://openalex.org/W6907525887"],"related_works":["https://openalex.org/W824100292","https://openalex.org/W2131060357","https://openalex.org/W3202295585","https://openalex.org/W406855141","https://openalex.org/W4236342353","https://openalex.org/W2496688599","https://openalex.org/W1964367640","https://openalex.org/W2117187715","https://openalex.org/W74898630","https://openalex.org/W4381571012"],"abstract_inverted_index":{"Abstract":[0],"Model":[1],"selection":[2,91,144],"aims":[3],"to":[4,57,107,116,149,158,163,186,197],"identify":[5],"a":[6,21,155,184],"sufficiently":[7],"well":[8],"performing":[9],"model":[10,19,60,90,143],"that":[11],"is":[12,65,105],"possibly":[13],"simpler":[14],"than":[15],"the":[16,26,36,55,78,84,99,129,172],"most":[17],"complex":[18],"among":[20],"pool":[22,85],"of":[23,39,80,86,102,131],"candidates.":[24],"However,":[25],"decision-making":[27],"process":[28],"itself":[29],"can":[30,53],"inadvertently":[31],"introduce":[32],"non-negligible":[33],"bias":[34,74,104,121,138],"when":[35,63,83,189,196],"cross-validation":[37,170],"estimates":[38,52],"predictive":[40],"performance":[41],"are":[42,93],"marred":[43],"by":[44],"excessive":[45],"noise.":[46],"In":[47],"finite":[48],"data":[49],"regimes,":[50],"cross-validated":[51],"encourage":[54],"statistician":[56],"select":[58],"one":[59],"over":[61],"another":[62],"it":[64],"not":[66,192],"actually":[67],"better":[68],"for":[69],"future":[70],"data.":[71],"While":[72],"this":[73,219],"remains":[75],"negligible":[76],"in":[77,96,134,218],"case":[79],"few":[81],"models,":[82],"candidates":[87],"grows,":[88],"and":[89,118,139,171,181,195,214],"decisions":[92],"compounded":[94,142],"(as":[95],"step-wise":[97],"selection),":[98],"expected":[100],"magnitude":[101],"selection-induced":[103,120,137,165],"likely":[106],"grow":[108],"too.":[109],"This":[110,152],"paper":[111],"introduces":[112],"an":[113],"efficient":[114],"approach":[115,133,175],"estimate":[117],"correct":[119],"based":[122],"on":[123,177,200],"order":[124],"statistics.":[125],"Numerical":[126],"experiments":[127],"demonstrate":[128],"reliability":[130],"our":[132],"estimating":[135],"both":[136],"over-fitting":[140],"along":[141],"decisions,":[145],"with":[146],"specific":[147],"application":[148],"forward":[150],"search.":[151],"work":[153],"represents":[154],"light-weight":[156],"alternative":[157],"more":[159,203],"computationally":[160,204],"expensive":[161,205],"approaches":[162],"correcting":[164],"bias,":[166],"such":[167],"as":[168],"nested":[169],"bootstrap.":[173],"Our":[174],"rests":[176],"several":[178],"theoretic":[179],"assumptions,":[180],"we":[182],"provide":[183],"diagnostic":[185],"help":[187],"understand":[188],"these":[190],"may":[191],"be":[193],"valid":[194],"fall":[198],"back":[199],"safer,":[201],"albeit":[202],"approaches.":[206],"The":[207],"accompanying":[208],"code":[209],"facilitates":[210],"its":[211],"practical":[212],"implementation":[213],"fosters":[215],"further":[216],"exploration":[217],"area.":[220]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}