{"id":"https://openalex.org/W4390675501","doi":"https://doi.org/10.1007/s10994-023-06439-1","title":"Learning de-biased regression trees and forests from complex samples","display_name":"Learning de-biased regression trees and forests from complex samples","publication_year":2024,"publication_date":"2024-01-08","ids":{"openalex":"https://openalex.org/W4390675501","doi":"https://doi.org/10.1007/s10994-023-06439-1"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-023-06439-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-023-06439-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-023-06439-1.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","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/s10994-023-06439-1.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085463590","display_name":"Malte Nalenz","orcid":"https://orcid.org/0000-0003-3439-4469"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Malte Nalenz","raw_affiliation_strings":["Department of Statistics, Ludwig-Maximilians-University, Ludwigstra\u00dfe 33, 80539, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0003-3439-4469","affiliations":[{"raw_affiliation_string":"Department of Statistics, Ludwig-Maximilians-University, Ludwigstra\u00dfe 33, 80539, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085820403","display_name":"Julian Rodemann","orcid":null},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Julian Rodemann","raw_affiliation_strings":["Department of Statistics, Ludwig-Maximilians-University, Ludwigstra\u00dfe 33, 80539, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Ludwig-Maximilians-University, Ludwigstra\u00dfe 33, 80539, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028359392","display_name":"Thomas Augustin","orcid":"https://orcid.org/0000-0002-1854-6226"},"institutions":[{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Augustin","raw_affiliation_strings":["Department of Statistics, Ludwig-Maximilians-University, Ludwigstra\u00dfe 33, 80539, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Ludwig-Maximilians-University, Ludwigstra\u00dfe 33, 80539, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085463590"],"corresponding_institution_ids":["https://openalex.org/I8204097"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":8.007,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.97608406,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"113","issue":"6","first_page":"3379","last_page":"3398"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11880","display_name":"Forest ecology and management","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/2309","display_name":"Nature and Landscape Conservation"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11880","display_name":"Forest ecology and management","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/2309","display_name":"Nature and Landscape Conservation"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10005","display_name":"Ecology and Vegetation Dynamics Studies","score":0.9772999882698059,"subfield":{"id":"https://openalex.org/subfields/2309","display_name":"Nature and Landscape Conservation"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10111","display_name":"Remote Sensing in Agriculture","score":0.9534000158309937,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.6847014427185059},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5495225787162781},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.5232745409011841},{"id":"https://openalex.org/keywords/sampling-design","display_name":"Sampling design","score":0.5110150575637817},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.4933449327945709},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4649454653263092},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.46195200085639954},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.453691303730011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4227922856807709},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.422555148601532},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.3967200815677643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34520119428634644}],"concepts":[{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.6847014427185059},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5495225787162781},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5232745409011841},{"id":"https://openalex.org/C75373757","wikidata":"https://www.wikidata.org/wiki/Q7410160","display_name":"Sampling design","level":3,"score":0.5110150575637817},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.4933449327945709},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4649454653263092},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.46195200085639954},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.453691303730011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4227922856807709},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.422555148601532},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.3967200815677643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34520119428634644},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10994-023-06439-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-023-06439-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-023-06439-1.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:epub.ub.uni-muenchen.de:116567","is_oa":true,"landing_page_url":"http://nbn-resolving.de/urn:nbn:de:bvb:19-epub-116567-9","pdf_url":"https://epub.ub.uni-muenchen.de/116567/1/s10994-023-06439-1.pdf","source":{"id":"https://openalex.org/S4306401845","display_name":"Open access LMU (Ludwid Maxmilian's Universitat Munchen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I8204097","host_organization_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","host_organization_lineage":["https://openalex.org/I8204097"],"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":"Machine Learning","raw_type":"doc-type:article"}],"best_oa_location":{"id":"doi:10.1007/s10994-023-06439-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-023-06439-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-023-06439-1.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"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":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Life in Land","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323390","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390675501.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W75203997","https://openalex.org/W644724742","https://openalex.org/W1678356000","https://openalex.org/W1918432791","https://openalex.org/W1968185435","https://openalex.org/W2022188138","https://openalex.org/W2033612074","https://openalex.org/W2044940981","https://openalex.org/W2066380803","https://openalex.org/W2086058521","https://openalex.org/W2123030147","https://openalex.org/W2125847307","https://openalex.org/W2131241448","https://openalex.org/W2148239836","https://openalex.org/W2157395790","https://openalex.org/W2215128562","https://openalex.org/W2612843304","https://openalex.org/W2613167874","https://openalex.org/W2613889334","https://openalex.org/W2787894218","https://openalex.org/W2911964244","https://openalex.org/W2963726264","https://openalex.org/W2969476445","https://openalex.org/W3008477519","https://openalex.org/W3102027041","https://openalex.org/W3159730769","https://openalex.org/W3202393439","https://openalex.org/W4200001778","https://openalex.org/W4200249081","https://openalex.org/W4212774754","https://openalex.org/W4233471163","https://openalex.org/W4238306122","https://openalex.org/W4300449175","https://openalex.org/W4300576158","https://openalex.org/W4315928673","https://openalex.org/W6626074796","https://openalex.org/W6688325169","https://openalex.org/W6722226382","https://openalex.org/W6931731073"],"related_works":["https://openalex.org/W4386259002","https://openalex.org/W1546989560","https://openalex.org/W3193043704","https://openalex.org/W3171520305","https://openalex.org/W2048488252","https://openalex.org/W4288365262","https://openalex.org/W2940614149","https://openalex.org/W4289884158","https://openalex.org/W2787485953","https://openalex.org/W3217432596"],"abstract_inverted_index":{"Abstract":[0],"Regression":[1],"trees":[2,74,106,144],"and":[3,12,81,107,133,162,179],"forests":[4,76,185,188],"are":[5,145],"widely":[6],"used":[7],"due":[8,96],"to":[9,93,97,118,146,153,173],"their":[10],"flexibility":[11],"predictive":[13,177],"accuracy.":[14],"Whereas":[15],"typical":[16],"tree":[17,91,119,135],"induction":[18],"assumes":[19],"independently":[20],"identically":[21],"distributed":[22],"(i.i.d.)":[23],"data,":[24],"in":[25,45,104,126,131,193],"many":[26],"applications":[27],"the":[28,55,65,98,101,124,127,134,143],"training":[29],"sample":[30,79,170],"follows":[31],"a":[32,49,69,163],"complex":[33,78,169],"sampling":[34,56],"structure.":[35,136],"This":[36,62,86],"includes":[37],"unequal":[38],"probability":[39],"sampling,":[40],"which":[41,197],"is":[42,87,139,151],"often":[43],"found":[44],"survey":[46,94,116],"data.":[47],"Then,":[48],"\u2018naive":[50],"estimation\u2019":[51],"that":[52,166],"simply":[53],"ignores":[54],"weights":[57],"may":[58],"be":[59,147],"substantially":[60],"biased.":[61],"article":[63],"analyzes":[64],"bias":[66,125],"arising":[67],"from":[68,115],"naive":[70],"estimation":[71,113],"of":[72,84,100,195],"regression":[73,105],"or":[75],"under":[77],"designs":[80,171],"proposes":[82],"ways":[83],"de-biasing.":[85],"achieved":[88],"by":[89],"bridging":[90],"learning":[92],"statistics,":[95],"correspondence":[99],"mean-squared-error":[102],"criterion":[103],"variance":[108,112],"estimation.":[109],"Transferring":[110],"population":[111],"approaches":[114],"statistics":[117],"induction,":[120],"indeed":[121],"considerably":[122],"reduces":[123],"resulting":[128],"trees,":[129],"both":[130],"predictions":[132],"The":[137],"latter":[138],"particularly":[140],"crucial":[141],"if":[142],"interpreted.":[148],"Our":[149],"methodology":[150],"extended":[152],"random":[154],"forests,":[155],"where":[156],"we":[157],"show":[158],"on":[159,190],"simulated":[160],"data":[161,204],"housing":[164],"dataset":[165],"correcting":[167],"for":[168,202],"leads":[172],"overall":[174],"much":[175],"better":[176],"accuracy":[178],"more":[180],"trustworthy":[181],"interpretation.":[182],"Interestingly,":[183],"corrected":[184],"can":[186],"surpass":[187],"learned":[189],"i.i.d.":[191],"samples":[192],"terms":[194],"accuracy,":[196],"also":[198],"has":[199],"important":[200],"implications":[201],"adaptive":[203],"collection":[205],"approaches.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-01-20T17:24:06.736184","created_date":"2025-10-10T00:00:00"}