{"id":"https://openalex.org/W4401159367","doi":"https://doi.org/10.48550/arxiv.2407.19804","title":"Imputation for prediction: beware of diminishing returns","display_name":"Imputation for prediction: beware of diminishing returns","publication_year":2024,"publication_date":"2024-07-29","ids":{"openalex":"https://openalex.org/W4401159367","doi":"https://doi.org/10.48550/arxiv.2407.19804"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2407.19804","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.19804","pdf_url":"https://arxiv.org/pdf/2407.19804","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2407.19804","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085618039","display_name":"Marine Le Morvan","orcid":"https://orcid.org/0000-0001-9899-221X","observed_orcids":["https://orcid.org/0000-0001-9899-221X"]},"institutions":[{"id":"https://openalex.org/I4405259981","display_name":"SODA: M\u00e9thodes computationnelles et math\u00e9matiques pour comprendre la soci\u00e9t\u00e9 et la sant\u00e9 \u00e0 partir de donn\u00e9es","ror":"https://ror.org/030zn8d06","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210126360","https://openalex.org/I4405259981"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Morvan, Marine Le","raw_affiliation_strings":["SODA","SODA - M\u00e9thodes computationnelles et math\u00e9matiques pour comprendre la soci\u00e9t\u00e9 et la sant\u00e9 \u00e0 partir de donn\u00e9es (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SODA","institution_ids":["https://openalex.org/I4405259981"]},{"raw_affiliation_string":"SODA - M\u00e9thodes computationnelles et math\u00e9matiques pour comprendre la soci\u00e9t\u00e9 et la sant\u00e9 \u00e0 partir de donn\u00e9es (France)","institution_ids":["https://openalex.org/I4405259981"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074733625","display_name":"Gael P. Varoquaux","orcid":"https://orcid.org/0000-0003-1076-5122","observed_orcids":["https://orcid.org/0000-0003-1076-5122"]},"institutions":[{"id":"https://openalex.org/I4210126360","display_name":"Centre Inria de Saclay","ror":"https://ror.org/0315e5x55","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210126360"]},{"id":"https://openalex.org/I4405259981","display_name":"SODA: M\u00e9thodes computationnelles et math\u00e9matiques pour comprendre la soci\u00e9t\u00e9 et la sant\u00e9 \u00e0 partir de donn\u00e9es","ror":"https://ror.org/030zn8d06","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210126360","https://openalex.org/I4405259981"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Varoquaux, Ga\u00ebl","raw_affiliation_strings":["SODA","Inria Saclay - Ile de France (1 rue Honor\u00e9 d'Estienne d'Orves\r\n\r\nB\u00e2timent Alan Turing\r\n\r\nCampus de l'\u00c9cole Polytechnique\r\n\r\n91120 Palaiseau - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SODA","institution_ids":["https://openalex.org/I4405259981"]},{"raw_affiliation_string":"Inria Saclay - Ile de France (1 rue Honor\u00e9 d'Estienne d'Orves\r\n\r\nB\u00e2timent Alan Turing\r\n\r\nCampus de l'\u00c9cole Polytechnique\r\n\r\n91120 Palaiseau - France)","institution_ids":["https://openalex.org/I4210126360"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.9053000211715698,"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/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.9053000211715698,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.03959999978542328,"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"}},{"id":"https://openalex.org/T13373","display_name":"Data Mining and Machine Learning Applications","score":0.004399999976158142,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/missing-data-imputation","display_name":"missing data imputation","score":0.9039999842643738},{"id":"https://openalex.org/keywords/prediction-accuracy","display_name":"prediction accuracy","score":0.7620000243186951},{"id":"https://openalex.org/keywords/missing-completely-at-random","display_name":"missing completely at random","score":0.6610000133514404},{"id":"https://openalex.org/keywords/imputation-accuracy","display_name":"imputation accuracy","score":0.5649999976158142}],"concepts":[{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.6648315191268921},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.4827827513217926},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.4169350564479828},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.32532399892807007},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.26908862590789795},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23113474249839783},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.12789249420166016}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:2407.19804","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.19804","pdf_url":"https://arxiv.org/pdf/2407.19804","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-04662937v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-04662937","pdf_url":"https://hal.science/hal-04662937v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"2024","raw_type":"info:eu-repo/semantics/preprint"},{"id":"pmh:oai:HAL:hal-04662937v2","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-04662937v2/document","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"ICLR 2025 - International Conference on Learning Representations, Apr 2025, Singapore, Singapore","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2407.19804","doi":"https://doi.org/10.48550/arxiv.2407.19804","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2407.19804","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2407.19804","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2407.19804","pdf_url":"https://arxiv.org/pdf/2407.19804","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401159367.pdf","grobid_xml":"https://content.openalex.org/works/W4401159367.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W2916442498","https://openalex.org/W3038289545","https://openalex.org/W3170720134","https://openalex.org/W4391556967"],"related_works":["https://openalex.org/W3038289545","https://openalex.org/W7062039165","https://openalex.org/W4303443567","https://openalex.org/W2943198600","https://openalex.org/W4200631471","https://openalex.org/W6982417098","https://openalex.org/W4414093378","https://openalex.org/W4391556967","https://openalex.org/W7172097716","https://openalex.org/W3141703049"],"abstract_inverted_index":{"Missing":[0],"values":[1],"are":[2],"prevalent":[3],"across":[4,72],"various":[5],"fields,":[6],"posing":[7],"challenges":[8],"for":[9,106,111,156],"training":[10],"and":[11,36,47,56,69,76],"deploying":[12],"predictive":[13,70,77],"models.":[14],"In":[15],"this":[16],"context,":[17],"imputation":[18,43,61,68,75,85,142],"is":[19,125],"a":[20,145],"common":[21],"practice,":[22],"driven":[23],"by":[24],"the":[25,119,122,128],"hope":[26],"that":[27,40,84,118],"accurate":[28],"imputations":[29,155],"will":[30],"enhance":[31],"predictions.":[32,66],"However,":[33],"recent":[34],"theoretical":[35],"empirical":[37,50],"studies":[38],"indicate":[39],"simple":[41],"constant":[42],"can":[44],"be":[45],"consistent":[46],"competitive.":[48],"This":[49],"study":[51],"aims":[52],"at":[53],"clarifying":[54],"if":[55],"when":[57,90,95],"investing":[58,152],"in":[59,132,153],"advanced":[60],"methods":[62],"yields":[63],"significantly":[64],"better":[65,154],"Relating":[67],"accuracies":[71],"combinations":[73],"of":[74,121],"models":[78],"on":[79,136,148],"19":[80],"datasets,":[81],"we":[82,115],"show":[83,117],"accuracy":[86],"matters":[87,103],"less":[88],"i)":[89],"using":[91],"expressive":[92],"models,":[93,140],"ii)":[94],"incorporating":[96],"missingness":[97,123],"indicators":[98],"as":[99],"complementary":[100],"inputs,":[101],"iii)":[102],"much":[104],"more":[105],"generated":[107],"linear":[108],"outcomes":[109],"than":[110],"real-data":[112,137],"outcomes.":[113],"Interestingly,":[114],"also":[116],"use":[120],"indicator":[124],"beneficial":[126],"to":[127],"prediction":[129,149],"performance,":[130],"even":[131],"MCAR":[133],"scenarios.":[134],"Overall,":[135],"with":[138],"powerful":[139],"improving":[141],"only":[143],"has":[144],"minor":[146],"effect":[147],"performance.":[150],"Thus,":[151],"improved":[157],"predictions":[158],"often":[159],"offers":[160],"limited":[161],"benefits.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":6}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-07-31T00:00:00"}