{"id":"https://openalex.org/W4407869598","doi":"https://doi.org/10.1080/10618600.2025.2469756","title":"Powerful Significance Testing for Unbalanced Clusters","display_name":"Powerful Significance Testing for Unbalanced Clusters","publication_year":2025,"publication_date":"2025-02-24","ids":{"openalex":"https://openalex.org/W4407869598","doi":"https://doi.org/10.1080/10618600.2025.2469756","pmid":"https://pubmed.ncbi.nlm.nih.gov/40857487"},"language":"en","primary_location":{"id":"doi:10.1080/10618600.2025.2469756","is_oa":false,"landing_page_url":"https://doi.org/10.1080/10618600.2025.2469756","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","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12338451/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076762109","display_name":"Thomas H. Keefe","orcid":"https://orcid.org/0000-0001-5565-1060"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I1333535994","display_name":"University of North Carolina Health Care","ror":"https://ror.org/00qz24g20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1333535994"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Thomas H. Keefe","raw_affiliation_strings":["Department of Statistics & O.R., UNC-Chapel Hill"],"raw_orcid":"https://orcid.org/0000-0001-5565-1060","affiliations":[{"raw_affiliation_string":"Department of Statistics & O.R., UNC-Chapel Hill","institution_ids":["https://openalex.org/I114027177","https://openalex.org/I1333535994"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112870622","display_name":"J. S. Marron","orcid":null},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]},{"id":"https://openalex.org/I1333535994","display_name":"University of North Carolina Health Care","ror":"https://ror.org/00qz24g20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1333535994"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. S. Marron","raw_affiliation_strings":["Department of Statistics & O.R., UNC-Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics & O.R., UNC-Chapel Hill","institution_ids":["https://openalex.org/I114027177","https://openalex.org/I1333535994"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076762109"],"corresponding_institution_ids":["https://openalex.org/I114027177","https://openalex.org/I1333535994"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01952606,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":"4","first_page":"1578","last_page":"1590"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9746000170707703,"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"}},"topics":[{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9746000170707703,"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/T11235","display_name":"Statistical Methods in Clinical Trials","score":0.9682000279426575,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9617000222206116,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5026073455810547},{"id":"https://openalex.org/keywords/significance-testing","display_name":"Significance testing","score":0.46084854006767273},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.4543759226799011},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4014219641685486},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2807272970676422},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.24761536717414856},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.244484543800354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5026073455810547},{"id":"https://openalex.org/C2984474657","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Significance testing","level":2,"score":0.46084854006767273},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.4543759226799011},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4014219641685486},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2807272970676422},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.24761536717414856},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.244484543800354}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1080/10618600.2025.2469756","is_oa":false,"landing_page_url":"https://doi.org/10.1080/10618600.2025.2469756","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"},{"id":"pmid:40857487","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40857487","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of computational and graphical statistics : a joint publication of American Statistical Association, Institute of Mathematical Statistics, Interface Foundation of North America","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12338451","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12338451/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Comput Graph Stat","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:12338451","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12338451/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Comput Graph Stat","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5554490311","display_name":null,"funder_award_id":"P30 AR072580","funder_id":"https://openalex.org/F4320337362","funder_display_name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases"}],"funders":[{"id":"https://openalex.org/F4320337362","display_name":"National Institute of Arthritis and Musculoskeletal and Skin Diseases","ror":"https://ror.org/006zn3t30"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W317995076","https://openalex.org/W562483513","https://openalex.org/W1548779692","https://openalex.org/W1964724001","https://openalex.org/W1991767154","https://openalex.org/W2044702943","https://openalex.org/W2069334182","https://openalex.org/W2071949631","https://openalex.org/W2097255042","https://openalex.org/W2118978333","https://openalex.org/W2127218421","https://openalex.org/W2150593711","https://openalex.org/W2158485828","https://openalex.org/W2161289668","https://openalex.org/W2234763457","https://openalex.org/W2259802687","https://openalex.org/W2795983726","https://openalex.org/W2797906965","https://openalex.org/W2890071928","https://openalex.org/W3027855333","https://openalex.org/W3111795212","https://openalex.org/W3184996951","https://openalex.org/W4210888701","https://openalex.org/W4224313447","https://openalex.org/W4249798375","https://openalex.org/W4285745043","https://openalex.org/W4378801953","https://openalex.org/W4392120869","https://openalex.org/W6733010041","https://openalex.org/W6810022582"],"related_works":["https://openalex.org/W1995180608","https://openalex.org/W1508359680","https://openalex.org/W2481981593","https://openalex.org/W2599060178","https://openalex.org/W791151000","https://openalex.org/W1505970868","https://openalex.org/W1604656656","https://openalex.org/W2371042144","https://openalex.org/W2951568014","https://openalex.org/W1913875882"],"abstract_inverted_index":{"Clustering":[0],"methods":[1],"are":[2],"popular":[3],"for":[4],"revealing":[5],"structure":[6],"in":[7,10,32,43,56,75,103],"data,":[8],"particularly":[9],"the":[11,25,44,48,66,77,91],"high-dimensional":[12,98],"setting":[13,46],"common":[14],"to":[15],"contemporary":[16],"data":[17],"science.":[18],"A":[19,107],"central":[20],"statistical":[21,33],"question":[22],"is":[23,36,40,65,73,110],"\u201care":[24],"clusters":[26,50],"really":[27],"there?\u201d":[28],"One":[29],"pioneering":[30],"method":[31,95],"cluster":[34],"validation":[35],"SigClust,":[37],"but":[38],"it":[39],"severely":[41],"underpowered":[42],"important":[45],"where":[47],"candidate":[49],"have":[51],"unbalanced":[52,78],"sizes,":[53],"such":[54],"as":[55],"rare":[57],"subtypes":[58],"of":[59,86,93,100],"disease.":[60],"We":[61,89],"show":[62],"why":[63],"this":[64],"case":[67],"and":[68,79],"propose":[69],"a":[70,83,97],"remedy":[71],"that":[72],"powerful":[74],"both":[76],"balanced":[80],"settings,":[81],"using":[82,96],"novel":[84],"generalization":[85],"k-means":[87],"clustering.":[88],"illustrate":[90],"value":[92],"our":[94],"dataset":[99],"gene":[101],"expression":[102],"kidney":[104],"cancer":[105],"patients.":[106],"Python":[108],"implementation":[109],"available":[111],"at":[112],"https://github.com/thomaskeefe/sigclust.":[113]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
