{"id":"https://openalex.org/W4390546905","doi":"https://doi.org/10.1080/10618600.2023.2301093","title":"Group-Orthogonal Subsampling for Hierarchical Data Based on Linear Mixed Models","display_name":"Group-Orthogonal Subsampling for Hierarchical Data Based on Linear Mixed Models","publication_year":2024,"publication_date":"2024-01-03","ids":{"openalex":"https://openalex.org/W4390546905","doi":"https://doi.org/10.1080/10618600.2023.2301093"},"language":"en","primary_location":{"id":"doi:10.1080/10618600.2023.2301093","is_oa":false,"landing_page_url":"https://doi.org/10.1080/10618600.2023.2301093","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/A5100713397","display_name":"Jiaqing Zhu","orcid":"https://orcid.org/0000-0001-9008-9093"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqing Zhu","raw_affiliation_strings":["Department of Statistics, KLAS and School of Mathematics and Statistics, Northeast Normal University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0001-9008-9093","affiliations":[{"raw_affiliation_string":"Department of Statistics, KLAS and School of Mathematics and Statistics, Northeast Normal University, Changchun, China","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086819279","display_name":"Lin Wang","orcid":"https://orcid.org/0000-0003-0888-6232"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lin Wang","raw_affiliation_strings":["Department of Statistics, Purdue University, West Lafayette, IN"],"raw_orcid":"https://orcid.org/0000-0003-0888-6232","affiliations":[{"raw_affiliation_string":"Department of Statistics, Purdue University, West Lafayette, IN","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052243305","display_name":"Fasheng Sun","orcid":"https://orcid.org/0000-0003-2410-4018"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fasheng Sun","raw_affiliation_strings":["Department of Statistics, KLAS and School of Mathematics and Statistics, Northeast Normal University, Changchun, China"],"raw_orcid":"https://orcid.org/0000-0003-2410-4018","affiliations":[{"raw_affiliation_string":"Department of Statistics, KLAS and School of Mathematics and Statistics, Northeast Normal University, Changchun, China","institution_ids":["https://openalex.org/I184983240"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5052243305"],"corresponding_institution_ids":["https://openalex.org/I184983240"],"apc_list":null,"apc_paid":null,"fwci":1.1976,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80437062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"33","issue":"3","first_page":"1037","last_page":"1046"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9984999895095825,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9984999895095825,"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/T10885","display_name":"Gene expression and cancer classification","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9955999851226807,"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/orthogonality","display_name":"Orthogonality","score":0.7574520111083984},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6488125920295715},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5375430583953857},{"id":"https://openalex.org/keywords/generalized-linear-mixed-model","display_name":"Generalized linear mixed model","score":0.5242919325828552},{"id":"https://openalex.org/keywords/mathematical-proof","display_name":"Mathematical proof","score":0.5220577716827393},{"id":"https://openalex.org/keywords/group","display_name":"Group (periodic table)","score":0.5101702213287354},{"id":"https://openalex.org/keywords/mixed-model","display_name":"Mixed model","score":0.5033401846885681},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.4160369634628296},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4070191979408264},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36660081148147583},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3308764696121216},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1700318455696106},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.16258329153060913},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.07540789246559143}],"concepts":[{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.7574520111083984},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6488125920295715},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5375430583953857},{"id":"https://openalex.org/C153720581","wikidata":"https://www.wikidata.org/wiki/Q5532490","display_name":"Generalized linear mixed model","level":2,"score":0.5242919325828552},{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.5220577716827393},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.5101702213287354},{"id":"https://openalex.org/C16012445","wikidata":"https://www.wikidata.org/wiki/Q1501135","display_name":"Mixed model","level":2,"score":0.5033401846885681},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.4160369634628296},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4070191979408264},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36660081148147583},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3308764696121216},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1700318455696106},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.16258329153060913},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.07540789246559143},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/10618600.2023.2301093","is_oa":false,"landing_page_url":"https://doi.org/10.1080/10618600.2023.2301093","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":[{"id":"https://openalex.org/G3193047092","display_name":null,"funder_award_id":"2020YFA0714102, 2022YFA1003701","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5164540766","display_name":null,"funder_award_id":"2412023YQ003","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6867594143","display_name":null,"funder_award_id":"12371259, 11971098","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W74197048","https://openalex.org/W2005991795","https://openalex.org/W2056594234","https://openalex.org/W2130645655","https://openalex.org/W2261854002","https://openalex.org/W2766451779","https://openalex.org/W2955312852","https://openalex.org/W2963921974","https://openalex.org/W2979582097","https://openalex.org/W3022172246","https://openalex.org/W3028903392","https://openalex.org/W3037232215","https://openalex.org/W3043888703","https://openalex.org/W3044420422","https://openalex.org/W3081894066","https://openalex.org/W3097162844","https://openalex.org/W3099924168","https://openalex.org/W3101247964","https://openalex.org/W3133949540","https://openalex.org/W3166349013","https://openalex.org/W3175075147","https://openalex.org/W3204212820","https://openalex.org/W3210246363","https://openalex.org/W3214583003","https://openalex.org/W4200609031","https://openalex.org/W4206341000","https://openalex.org/W4214812430","https://openalex.org/W4220892252","https://openalex.org/W4230925129","https://openalex.org/W4249150173","https://openalex.org/W4284893198","https://openalex.org/W4285067809","https://openalex.org/W4312225576","https://openalex.org/W4320491312","https://openalex.org/W4388085831","https://openalex.org/W4392357959","https://openalex.org/W6703949738"],"related_works":["https://openalex.org/W4307324678","https://openalex.org/W2021312236","https://openalex.org/W2186257539","https://openalex.org/W2895736713","https://openalex.org/W2477652392","https://openalex.org/W1551599973","https://openalex.org/W2356286374","https://openalex.org/W4289422681","https://openalex.org/W2953058310","https://openalex.org/W2065965622"],"abstract_inverted_index":{"Hierarchical":[0],"data":[1,49,79,89,136],"analysis":[2],"is":[3,15,26,125],"crucial":[4],"in":[5,57,100],"various":[6],"fields":[7],"for":[8,18,73,107],"making":[9],"discoveries.":[10],"The":[11],"linear":[12,109],"mixed":[13,110],"model":[14],"often":[16],"used":[17],"training":[19],"hierarchical":[20,58,78],"data,":[21],"but":[22],"its":[23],"parameter":[24],"estimation":[25],"computationally":[27],"expensive,":[28],"especially":[29],"with":[30,87],"big":[31],"data.":[32,59],"Subsampling":[33],"techniques":[34],"have":[35],"been":[36],"developed":[37],"to":[38,127],"address":[39,61],"this":[40,62],"challenge.":[41],"However,":[42],"most":[43],"existing":[44],"subsampling":[45,71],"methods":[46],"assume":[47],"homogeneous":[48],"and":[50,93,105,121,133,142],"do":[51],"not":[52],"consider":[53],"the":[54],"possible":[55],"heterogeneity":[56],"To":[60],"limitation,":[63],"we":[64],"develop":[65],"a":[66,134],"new":[67],"approach":[68],"called":[69],"group-orthogonal":[70],"(GOSS)":[72],"selecting":[74],"informative":[75],"subsets":[76],"of":[77,113],"that":[80,102],"may":[81],"exhibit":[82],"heterogeneity.":[83],"GOSS":[84,117,124],"selects":[85],"subdata":[86,101,118],"balanced":[88],"size":[90],"among":[91],"groups":[92],"combinatorial":[94],"orthogonality":[95],"within":[96],"each":[97],"group,":[98],"resulting":[99],"are":[103,119,146],"D-":[104],"A-optimal":[106],"building":[108],"models.":[111],"Estimators":[112],"parameters":[114],"trained":[115],"on":[116],"consistent":[120],"asymptotically":[122],"normal.":[123],"shown":[126],"be":[128],"numerically":[129],"appealing":[130],"via":[131],"simulations":[132],"real":[135],"application.":[137],"Theoretical":[138],"proofs,":[139],"R":[140],"codes,":[141],"supplementary":[143,150],"numerical":[144],"results":[145],"accessible":[147],"online":[148],"as":[149],"materials.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}