{"id":"https://openalex.org/W2586011290","doi":"https://doi.org/10.1007/s10618-017-0520-3","title":"Identifying consistent statements about numerical data with dispersion-corrected subgroup discovery","display_name":"Identifying consistent statements about numerical data with dispersion-corrected subgroup discovery","publication_year":2017,"publication_date":"2017-06-28","ids":{"openalex":"https://openalex.org/W2586011290","doi":"https://doi.org/10.1007/s10618-017-0520-3","mag":"2586011290"},"language":"en","primary_location":{"id":"doi:10.1007/s10618-017-0520-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-017-0520-3","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10618-017-0520-3.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"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":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007%2Fs10618-017-0520-3.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Mario Boley","orcid":"https://orcid.org/0000-0002-0704-4968"},"institutions":[{"id":"https://openalex.org/I2800875726","display_name":"Fritz Haber Institute of the Max Planck Society","ror":"https://ror.org/03k9qs827","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I2800875726"]},{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Mario Boley","raw_affiliation_strings":["Fritz Haber Institute of the Max Planck Society, Berlin, Germany","Max Planck Institute for Informatics and Saarland University, Saarbr\u00fccken, Germany"],"raw_orcid":"https://orcid.org/0000-0002-0704-4968","affiliations":[{"raw_affiliation_string":"Fritz Haber Institute of the Max Planck Society, Berlin, Germany","institution_ids":["https://openalex.org/I2800875726"]},{"raw_affiliation_string":"Max Planck Institute for Informatics and Saarland University, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712","https://openalex.org/I91712215"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bryan R. Goldsmith","orcid":"https://orcid.org/0000-0003-1264-8018"},"institutions":[{"id":"https://openalex.org/I2800875726","display_name":"Fritz Haber Institute of the Max Planck Society","ror":"https://ror.org/03k9qs827","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I2800875726"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bryan R. Goldsmith","raw_affiliation_strings":["Fritz Haber Institute of the Max Planck Society, Berlin, Germany"],"raw_orcid":"https://orcid.org/0000-0003-1264-8018","affiliations":[{"raw_affiliation_string":"Fritz Haber Institute of the Max Planck Society, Berlin, Germany","institution_ids":["https://openalex.org/I2800875726"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Luca M. Ghiringhelli","orcid":null},"institutions":[{"id":"https://openalex.org/I2800875726","display_name":"Fritz Haber Institute of the Max Planck Society","ror":"https://ror.org/03k9qs827","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I2800875726"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Luca M. Ghiringhelli","raw_affiliation_strings":["Fritz Haber Institute of the Max Planck Society, Berlin, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fritz Haber Institute of the Max Planck Society, Berlin, Germany","institution_ids":["https://openalex.org/I2800875726"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jilles Vreeken","orcid":"https://orcid.org/0000-0002-2310-2806"},"institutions":[{"id":"https://openalex.org/I4210109712","display_name":"Max Planck Institute for Informatics","ror":"https://ror.org/01w19ak89","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210109712"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jilles Vreeken","raw_affiliation_strings":["Max Planck Institute for Informatics and Saarland University, Saarbr\u00fccken, Germany"],"raw_orcid":"https://orcid.org/0000-0002-2310-2806","affiliations":[{"raw_affiliation_string":"Max Planck Institute for Informatics and Saarland University, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210109712","https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2800875726","https://openalex.org/I4210109712","https://openalex.org/I91712215"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":2.6342,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.92247397,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"31","issue":"5","first_page":"1391","last_page":"1418"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.121799997985363,"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/T10136","display_name":"Statistical Methods and Inference","score":0.121799997985363,"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/T11871","display_name":"Advanced Statistical Methods and Models","score":0.04969999939203262,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.03579999879002571,"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/estimator","display_name":"Estimator","score":0.8256000280380249},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.45170000195503235},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.4334000051021576},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.3953999876976013},{"id":"https://openalex.org/keywords/dispersion","display_name":"Dispersion (optics)","score":0.36970001459121704},{"id":"https://openalex.org/keywords/subgroup-analysis","display_name":"Subgroup analysis","score":0.35850000381469727}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.8256000280380249},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5626999735832214},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.45170000195503235},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.4334000051021576},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4174000024795532},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3953999876976013},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38440001010894775},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.37380000948905945},{"id":"https://openalex.org/C177562468","wikidata":"https://www.wikidata.org/wiki/Q182893","display_name":"Dispersion (optics)","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C187960798","wikidata":"https://www.wikidata.org/wiki/Q7631152","display_name":"Subgroup analysis","level":3,"score":0.35850000381469727},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3490999937057495},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C193244246","wikidata":"https://www.wikidata.org/wiki/Q5432696","display_name":"False discovery rate","level":3,"score":0.30799999833106995},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C181243257","wikidata":"https://www.wikidata.org/wiki/Q1693522","display_name":"Sample mean and sample covariance","level":3,"score":0.27489998936653137},{"id":"https://openalex.org/C183905921","wikidata":"https://www.wikidata.org/wiki/Q1038757","display_name":"Multiple comparisons problem","level":2,"score":0.26739999651908875}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s10618-017-0520-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-017-0520-3","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10618-017-0520-3.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"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":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1701.07696","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1701.07696","pdf_url":"https://arxiv.org/pdf/1701.07696","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.1007/s10618-017-0520-3","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-017-0520-3","pdf_url":"https://link.springer.com/content/pdf/10.1007%2Fs10618-017-0520-3.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"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":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8625612407","display_name":null,"funder_award_id":"676580","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320308269","display_name":"Alexander von Humboldt-Stiftung","ror":"https://ror.org/012kf4317"},{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320322434","display_name":"Max-Planck-Gesellschaft","ror":"https://ror.org/01hhn8329"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2586011290.pdf","grobid_xml":"https://content.openalex.org/works/W2586011290.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W19763141","https://openalex.org/W1484732323","https://openalex.org/W1486664027","https://openalex.org/W1508174699","https://openalex.org/W1531520279","https://openalex.org/W1549565124","https://openalex.org/W1564483404","https://openalex.org/W1575009136","https://openalex.org/W1994972455","https://openalex.org/W2033534831","https://openalex.org/W2035196341","https://openalex.org/W2035946364","https://openalex.org/W2066771339","https://openalex.org/W2092209977","https://openalex.org/W2103459555","https://openalex.org/W2118349699","https://openalex.org/W2129027474","https://openalex.org/W2149474501","https://openalex.org/W2153472243","https://openalex.org/W2160406974","https://openalex.org/W2171666258","https://openalex.org/W2238902321","https://openalex.org/W2338621248","https://openalex.org/W2511911140","https://openalex.org/W2564078846"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"algorithms":[1],"for":[2,49,69],"subgroup":[3,51,76,81],"discovery":[4,52],"with":[5,142],"numerical":[6],"targets":[7],"do":[8],"not":[9],"optimize":[10],"the":[11,18,31,45,80,89,94,103,108],"error":[12],"or":[13,27],"target":[14],"variable":[15],"dispersion":[16,86,99],"of":[17,57,124],"groups":[19],"they":[20],"find.":[21],"This":[22],"often":[23],"leads":[24],"to":[25,53],"unreliable":[26],"inconsistent":[28],"statements":[29],"about":[30],"data,":[32],"rendering":[33],"practical":[34],"applications,":[35],"especially":[36],"in":[37],"scientific":[38],"domains,":[39],"futile.":[40],"Therefore,":[41],"we":[42,60],"here":[43],"extend":[44],"optimistic":[46],"estimator":[47],"framework":[48],"optimal":[50],"a":[54,85,114,121],"new":[55],"class":[56],"objective":[58],"functions:":[59],"show":[61],"how":[62],"tight":[63],"estimators":[64],"can":[65],"be":[66],"computed":[67],"efficiently":[68],"all":[70],"functions":[71],"that":[72],"are":[73],"determined":[74],"by":[75],"size":[77],"(non-decreasing":[78],"dependence),":[79],"median":[82,90],"value,":[83],"and":[84,138],"measure":[87],"around":[88],"(non-increasing":[91],"dependence).":[92],"In":[93],"important":[95],"special":[96],"case":[97],"when":[98,128],"is":[100,135],"measured":[101],"using":[102],"mean":[104],"absolute":[105],"deviation":[106],"from":[107],"median,":[109],"this":[110,133],"novel":[111],"approach":[112,134],"yields":[113],"linear":[115],"time":[116],"algorithm.":[117],"Empirical":[118],"evaluation":[119],"on":[120],"wide":[122],"range":[123],"datasets":[125],"shows":[126],"that,":[127],"used":[129],"within":[130],"branch-and-bound":[131],"search,":[132],"highly":[136],"efficient":[137],"indeed":[139],"discovers":[140],"subgroups":[141],"much":[143],"smaller":[144],"errors.":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2}],"updated_date":"2026-05-23T08:51:43.019350","created_date":"2017-02-10T00:00:00"}