{"id":"https://openalex.org/W3175769723","doi":"https://doi.org/10.1080/10618600.2021.1923520","title":"The Holdout Randomization Test for Feature Selection in Black Box Models","display_name":"The Holdout Randomization Test for Feature Selection in Black Box Models","publication_year":2021,"publication_date":"2021-06-17","ids":{"openalex":"https://openalex.org/W3175769723","doi":"https://doi.org/10.1080/10618600.2021.1923520","mag":"3175769723"},"language":"en","primary_location":{"id":"doi:10.1080/10618600.2021.1923520","is_oa":false,"landing_page_url":"https://doi.org/10.1080/10618600.2021.1923520","pdf_url":null,"source":{"id":"https://openalex.org/S76159266","display_name":"Journal of Computational and Graphical Statistics","issn_l":"1061-8600","issn":["1061-8600","1537-2715"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational and Graphical Statistics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5006383763","display_name":"Wesley Tansey","orcid":"https://orcid.org/0000-0002-5294-4228"},"institutions":[{"id":"https://openalex.org/I1334819555","display_name":"Memorial Sloan Kettering Cancer Center","ror":"https://ror.org/02yrq0923","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1334819555"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wesley Tansey","raw_affiliation_strings":["Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center, New York, NY;;"],"affiliations":[{"raw_affiliation_string":"Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center, New York, NY;;","institution_ids":["https://openalex.org/I1334819555"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077406767","display_name":"Victor Veitch","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Victor Veitch","raw_affiliation_strings":["Department of Statistics, Columbia University, New York, NY;;"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, Columbia University, New York, NY;;","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034098591","display_name":"Haoran Zhang","orcid":"https://orcid.org/0000-0002-4128-0219"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoran Zhang","raw_affiliation_strings":["Department of Computer Science, University of Texas at Austin, TX;;"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin, TX;;","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056128255","display_name":"Ra\u00fal Rabad\u00e1n","orcid":"https://orcid.org/0000-0001-7946-9255"},"institutions":[{"id":"https://openalex.org/I2799503643","display_name":"Columbia University Irving Medical Center","ror":"https://ror.org/01esghr10","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2799503643"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raul Rabadan","raw_affiliation_strings":["Department of Systems Biology, Columbia University Medical Center, New York, NY;;"],"affiliations":[{"raw_affiliation_string":"Department of Systems Biology, Columbia University Medical Center, New York, NY;;","institution_ids":["https://openalex.org/I2799503643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070920982","display_name":"David M. Blei","orcid":"https://orcid.org/0000-0002-5588-4611"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David M. Blei","raw_affiliation_strings":["Departments of Computer Science and Statistics, Columbia University, New York, NY"],"affiliations":[{"raw_affiliation_string":"Departments of Computer Science and Statistics, Columbia University, New York, NY","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5006383763"],"corresponding_institution_ids":["https://openalex.org/I1334819555"],"apc_list":null,"apc_paid":null,"fwci":2.5153,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91024456,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"31","issue":"1","first_page":"151","last_page":"162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9994999766349792,"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/T11235","display_name":"Statistical Methods in Clinical Trials","score":0.9983000159263611,"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":0.9973000288009644,"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/heuristics","display_name":"Heuristics","score":0.8240042924880981},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6593747138977051},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6178916692733765},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.5550774931907654},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5053822994232178},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.49626046419143677},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.47734931111335754},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.4619835317134857},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4540194272994995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38342055678367615},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3286142349243164},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3208125829696655},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20988374948501587}],"concepts":[{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.8240042924880981},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6593747138977051},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6178916692733765},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.5550774931907654},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5053822994232178},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.49626046419143677},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.47734931111335754},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.4619835317134857},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4540194272994995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38342055678367615},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3286142349243164},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3208125829696655},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20988374948501587},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/10618600.2021.1923520","is_oa":false,"landing_page_url":"https://doi.org/10.1080/10618600.2021.1923520","pdf_url":null,"source":{"id":"https://openalex.org/S76159266","display_name":"Journal of Computational and Graphical Statistics","issn_l":"1061-8600","issn":["1061-8600","1537-2715"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational and Graphical Statistics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1555806843","https://openalex.org/W1596515083","https://openalex.org/W1995119847","https://openalex.org/W2043398720","https://openalex.org/W2082213488","https://openalex.org/W2084341220","https://openalex.org/W2110065044","https://openalex.org/W2157121418","https://openalex.org/W2192203593","https://openalex.org/W2282821441","https://openalex.org/W2339195677","https://openalex.org/W2589330732","https://openalex.org/W2618851150","https://openalex.org/W2731142262","https://openalex.org/W2781844902","https://openalex.org/W2788199784","https://openalex.org/W2884093636","https://openalex.org/W2885383314","https://openalex.org/W2891979008","https://openalex.org/W2901837190","https://openalex.org/W2962862931","https://openalex.org/W2963365341","https://openalex.org/W2963371845","https://openalex.org/W2964060211","https://openalex.org/W3042860357","https://openalex.org/W3103643510","https://openalex.org/W3106984542","https://openalex.org/W3120610311","https://openalex.org/W4238306122","https://openalex.org/W6753676597","https://openalex.org/W6947929836"],"related_works":["https://openalex.org/W2280422768","https://openalex.org/W3143197806","https://openalex.org/W4252555497","https://openalex.org/W3121175838","https://openalex.org/W3016293053","https://openalex.org/W2401723157","https://openalex.org/W2952904874","https://openalex.org/W4389302559","https://openalex.org/W1690653314","https://openalex.org/W2053033682"],"abstract_inverted_index":{"We":[0,90],"propose":[1,58],"the":[2,24,53,87,92,99,128],"holdout":[3],"randomization":[4,26],"test":[5,27],"(HRT),":[6],"an":[7],"approach":[8],"to":[9,63,75,94,107,124],"feature":[10],"selection":[11],"using":[12],"black":[13],"box":[14],"predictive":[15,41,112],"models.":[16,113],"The":[17,36,114],"HRT":[18,37,54,93],"is":[19,131],"a":[20,45,59,79],"specialized":[21],"version":[22],"of":[23,61,86],"conditional":[25],"(CRT)":[28],"that":[29],"uses":[30],"data":[31],"splitting":[32],"for":[33,48,111,137],"feasible":[34],"computation.":[35,69],"works":[38],"with":[39],"any":[40],"model":[42],"and":[43,66],"produces":[44],"valid":[46],"p-value":[47],"each":[49],"feature.":[50],"To":[51],"make":[52],"more":[55],"practical,":[56],"we":[57],"set":[60],"extensions":[62,73],"maximize":[64],"power":[65,77],"speed":[67],"up":[68],"In":[70],"simulations,":[71],"these":[72],"lead":[74],"greater":[76],"than":[78],"competing":[80],"knockoffs-based":[81],"approach,":[82],"without":[83],"sacrificing":[84],"control":[85],"error":[88],"rate.":[89],"apply":[91],"two":[95],"case":[96],"studies":[97],"from":[98],"scientific":[100],"literature":[101],"where":[102],"heuristics":[103,119],"were":[104],"originally":[105],"used":[106],"select":[108],"important":[109],"features":[110],"results":[115],"illustrate":[116],"how":[117],"such":[118],"can":[120],"be":[121],"misleading":[122],"relative":[123],"principled":[125],"methods":[126],"like":[127],"HRT.":[129],"Code":[130],"available":[132,141],"at":[133],"https://github.com/tansey/hrt.":[134],"Supplementary":[135],"materials":[136],"this":[138],"article":[139],"are":[140],"online.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}