{"id":"https://openalex.org/W2142713577","doi":"https://doi.org/10.1016/j.patcog.2007.11.008","title":"Do unbalanced data have a negative effect on LDA?","display_name":"Do unbalanced data have a negative effect on LDA?","publication_year":2007,"publication_date":"2007-11-26","ids":{"openalex":"https://openalex.org/W2142713577","doi":"https://doi.org/10.1016/j.patcog.2007.11.008","mag":"2142713577"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.patcog.2007.11.008","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/6833/1/6833.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079361172","display_name":"Jing\u2010Hao Xue","orcid":"https://orcid.org/0000-0003-1174-610X"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jing-Hao Xue","raw_affiliation_strings":["Department of Statistics, University of Glasgow, Glasgow, G12 8QQ, UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Glasgow, Glasgow, G12 8QQ, UK#TAB#","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051905013","display_name":"D. M. Titterington","orcid":null},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"D. Michael Titterington","raw_affiliation_strings":["Department of Statistics, University of Glasgow, Glasgow, G12 8QQ, UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Glasgow, Glasgow, G12 8QQ, UK#TAB#","institution_ids":["https://openalex.org/I7882870"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2710,"currency":"USD","value_usd":2710,"provenance":"doaj"},"apc_paid":null,"fwci":0.426,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":64,"citation_normalized_percentile":{"value":0.962417,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"41","issue":"5","first_page":"1558","last_page":"1571"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Handling Imbalanced Data in Classification Problems","score":0.9998,"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/T11652","display_name":"Handling Imbalanced Data in Classification Problems","score":0.9998,"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/T11871","display_name":"Detection and Handling of Multicollinearity in Regression Analysis","score":0.9833,"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/T13030","display_name":"Statistical Methods for Sensitive Survey Questions","score":0.9442,"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/imbalanced-data","display_name":"Imbalanced Data","score":0.623238},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5264455}],"concepts":[{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.8036203},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5264455},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.5171937},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.50675064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4930291},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4645289},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4455849},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43104875},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3765244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37498045},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.080660135},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.patcog.2007.11.008","pdf_url":null,"source":{"id":"https://openalex.org/S414566","display_name":"Pattern Recognition","issn_l":"0031-3203","issn":["0031-3203","1873-5142"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/6833/1/6833.pdf","pdf_url":"https://eprints.gla.ac.uk/6833/1/6833.pdf","source":{"id":"https://openalex.org/S4306400411","display_name":"Enlighten: Publications (The University of Glasgow)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I7882870","host_organization_name":"University of Glasgow","host_organization_lineage":["https://openalex.org/I7882870"],"host_organization_lineage_names":["University of Glasgow"],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/6833/1/6833.pdf","pdf_url":"https://eprints.gla.ac.uk/6833/1/6833.pdf","source":{"id":"https://openalex.org/S4306400411","display_name":"Enlighten: Publications (The University of Glasgow)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I7882870","host_organization_name":"University of Glasgow","host_organization_lineage":["https://openalex.org/I7882870"],"host_organization_lineage_names":["University of Glasgow"],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.69,"id":"https://metadata.un.org/sdg/10"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":17,"referenced_works":["https://openalex.org/W1965751196","https://openalex.org/W1965895350","https://openalex.org/W2053724458","https://openalex.org/W2055653482","https://openalex.org/W2084812512","https://openalex.org/W2114968414","https://openalex.org/W2120100126","https://openalex.org/W2129476886","https://openalex.org/W2155653793","https://openalex.org/W2157825442","https://openalex.org/W2163614729","https://openalex.org/W2164296439","https://openalex.org/W2316326124","https://openalex.org/W2796765386","https://openalex.org/W3009784374","https://openalex.org/W3111627855","https://openalex.org/W4239711916"],"related_works":["https://openalex.org/W4232979854","https://openalex.org/W32502520","https://openalex.org/W2380666260","https://openalex.org/W2160698598","https://openalex.org/W2156856390","https://openalex.org/W2038099157","https://openalex.org/W2023698157","https://openalex.org/W1983848850","https://openalex.org/W1921169094","https://openalex.org/W1809065030"],"abstract_inverted_index":{"For":[0],"two-class":[1],"discrimination,":[2],"Xie":[3,59,120],"and":[4,16,60,72,121,133,142,172,287],"Qiu":[5,61,122],"[The":[6,62,123],"effect":[7,44,63,124,245],"of":[8,30,48,64,125,164,181,184,190,192,204,207,215,249,257],"imbalanced":[9,65,126],"data":[10,39,57,66,127,168,240,260],"sets":[11,67,128,261],"on":[12,45,68,129,160,246],"LDA:":[13,69,130],"a":[14,36,42,70,105,131,147,237,243,277],"theoretical":[15,71,116,132],"empirical":[17,73,82,134,171,230],"analysis,":[18,74,135],"Pattern":[19,75,136],"Recognition":[20,76,137],"40":[21,77,138],"(2)":[22,78,139],"(2007)":[23,79,140],"557\u2013562]":[24,80],"claimed":[25],"that,":[26,176],"when":[27],"covariance":[28,267,273],"matrices":[29,274],"the":[31,46,86,92,98,161,179,182,188,202,205,211,234,247,255,281],"two":[32],"classes":[33],"were":[34],"unequal,":[35],"(class)":[37,238],"unbalanced":[38,167,239],"set":[40,241],"had":[41],"negative":[43,244],"performance":[47,99,163,191,214,248,256,284],"linear":[49],"discriminant":[50],"analysis":[51,117],"(LDA).":[52],"Through":[53],"re-balancing":[54,195,218,253],"10":[55],"real-world":[56],"sets,":[58],"provided":[81],"evidence":[83,231],"to":[84,146,154,232],"support":[85,233],"claim":[87,106,235],"using":[88],"AUC":[89,143,185],"(Area":[90],"Under":[91],"receiver":[93],"operating":[94],"characteristic":[95],"Curve)":[96],"as":[97],"metric.":[100],"We":[101],"suggest":[102,175],"that":[103,152,236,270],"such":[104],"is":[107,113,196,219,227,275],"vague":[108],"if":[109],"not":[110,276],"misleading,":[111],"there":[112,226],"no":[114,228],"solid":[115],"presented":[118],"in":[119,200,213,283],"557\u2013562],":[141],"can":[144],"lead":[145],"quite":[148],"different":[149],"conclusion":[150],"from":[151,194,217,223],"led":[153],"by":[155],"misclassification":[156],"error":[157],"rate":[158],"(ER)":[159],"discrimination":[162],"LDA":[165,258],"for":[166,177,259,280],"sets.":[169],"Our":[170],"simulation":[173],"studies":[174],"LDA,":[178],"increase":[180,203],"median":[183,206],"(and":[186,209],"thus":[187,210],"improvement":[189],"LDA)":[193,216],"relatively":[197,220],"small,":[198],"while,":[199],"contrast,":[201],"ER":[208],"decline":[212],"large.":[221],"Therefore,":[222],"our":[224],"study,":[225],"reliable":[229],"has":[242],"LDA.":[250],"In":[251],"addition,":[252],"affects":[254],"with":[262],"either":[263],"equal":[264],"or":[265],"unequal":[266,272],"matrices,":[268],"indicating":[269],"having":[271],"key":[278],"reason":[279],"difference":[282],"between":[285],"original":[286],"re-balanced":[288],"data.":[289]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2142713577","counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":5}],"updated_date":"2024-11-22T18:18:35.666856","created_date":"2016-06-24"}