{"id":"https://openalex.org/W7204147406","doi":"https://doi.org/10.1371/journal.pone.0342286","title":"Separation-like irregularity and sample size optimism in high-discrimination logistic prediction models","display_name":"Separation-like irregularity and sample size optimism in high-discrimination logistic prediction models","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204147406","doi":"https://doi.org/10.1371/journal.pone.0342286","pmid":"https://pubmed.ncbi.nlm.nih.gov/42636249"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pone.0342286","doi":"https://doi.org/10.1371/journal.pone.0342286","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pone.0342286","pdf_url":"https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0342286&type=printable","source":{"id":"https://openalex.org/S202381698","display_name":"PLoS ONE","issn_l":"1932-6203","issn":["1932-6203"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","erih-plus","jufo-1","ki-jl-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS One","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0342286&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086812562","display_name":"Ye Liang","orcid":"https://orcid.org/0000-0002-6513-8962","observed_orcids":["https://orcid.org/0000-0002-6513-8962"]},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ye Liang","raw_affiliation_strings":["Department of Industrial and Systems Engineering, University of Iowa, Iowa City, Iowa, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial and Systems Engineering, University of Iowa, Iowa City, Iowa, United States of America","institution_ids":["https://openalex.org/I126307644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009882066","display_name":"Louis Shuo Wang","orcid":"https://orcid.org/0009-0007-0977-7894","observed_orcids":["https://orcid.org/0009-0007-0977-7894"]},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Louis Shuo Wang","raw_affiliation_strings":["Department of Mathematics, University of Tennessee, Knoxville, Tennessee, United States of America"],"raw_orcid":"https://orcid.org/0009-0007-0977-7894","affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of Tennessee, Knoxville, Tennessee, United States of America","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024934818","display_name":"Jiguang Yu","orcid":"https://orcid.org/0009-0007-9758-6237","observed_orcids":["https://orcid.org/0009-0007-9758-6237"]},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiguang Yu","raw_affiliation_strings":["College of Engineering, Boston University, Boston, Massachusetts, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering, Boston University, Boston, Massachusetts, United States of America","institution_ids":["https://openalex.org/I111088046"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5147975256","display_name":"Xin Zan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126307644","display_name":"University of Iowa","ror":"https://ror.org/036jqmy94","country_code":"US","type":"education","lineage":["https://openalex.org/I126307644"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Zan","raw_affiliation_strings":["Department of Industrial and Systems Engineering, University of Iowa, Iowa City, Iowa, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial and Systems Engineering, University of Iowa, Iowa City, Iowa, United States of America","institution_ids":["https://openalex.org/I126307644"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009882066"],"corresponding_institution_ids":["https://openalex.org/I75027704"],"apc_list":{"value":2382,"currency":"USD","value_usd":2382},"apc_paid":{"value":2382,"currency":"USD","value_usd":2382},"fwci":5.27,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.96476481,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":"21","issue":"8","first_page":"e0342286","last_page":"e0342286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14374","display_name":"Statistical Methods in Epidemiology","score":0.9824000000953674,"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/T14374","display_name":"Statistical Methods in Epidemiology","score":0.9824000000953674,"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/T10136","display_name":"Statistical Methods and Inference","score":0.007400000002235174,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.0027000000700354576,"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/sample-size-calculation","display_name":"sample size determination","score":0.6679999828338623},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"logistic regression","score":0.6299999952316284},{"id":"https://openalex.org/keywords/out-of-sample-validation","display_name":"out-of-sample validation","score":0.7139999866485596},{"id":"https://openalex.org/keywords/risk-prediction-model","display_name":"risk prediction model","score":0.5299999713897705},{"id":"https://openalex.org/keywords/prevalence","display_name":"prevalence","score":0.38100001215934753},{"id":"https://openalex.org/keywords/signal-density","display_name":"signal density","score":0.453000009059906}],"concepts":[{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.7297999858856201},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.7200999855995178},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.5878999829292297},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.570900022983551},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.517799973487854},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5044999718666077},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4699000120162964},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.4025000035762787},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.3418999910354614},{"id":"https://openalex.org/C3020318244","wikidata":"https://www.wikidata.org/wiki/Q4812187","display_name":"Large sample","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C68443243","wikidata":"https://www.wikidata.org/wiki/Q2786686","display_name":"Quartile","level":3,"score":0.27320000529289246},{"id":"https://openalex.org/C180802074","wikidata":"https://www.wikidata.org/wiki/Q1052379","display_name":"Logistic function","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2623000144958496},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C181243257","wikidata":"https://www.wikidata.org/wiki/Q1693522","display_name":"Sample mean and sample covariance","level":3,"score":0.2563000023365021},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.2540000081062317},{"id":"https://openalex.org/C204017024","wikidata":"https://www.wikidata.org/wiki/Q485446","display_name":"Optimism","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.25119999051094055}],"mesh":[{"descriptor_ui":"D000098437","descriptor_name":"Prediction Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000098437","descriptor_name":"Prediction Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009010","descriptor_name":"Monte Carlo Method","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009010","descriptor_name":"Monte Carlo Method","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016015","descriptor_name":"Logistic Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016015","descriptor_name":"Logistic Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018401","descriptor_name":"Sample Size","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018401","descriptor_name":"Sample Size","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1371/journal.pone.0342286","doi":"https://doi.org/10.1371/journal.pone.0342286","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pone.0342286","pdf_url":"https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0342286&type=printable","source":{"id":"https://openalex.org/S202381698","display_name":"PLoS ONE","issn_l":"1932-6203","issn":["1932-6203"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","erih-plus","jufo-1","ki-jl-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS One","raw_type":"journal-article"},{"id":"pmid:42636249","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42636249","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,"listed_in":[],"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":"PloS one","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13502705","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13502705/","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13502705/pdf/pone.0342286.pdf","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS One","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1371/journal.pone.0342286","doi":"https://doi.org/10.1371/journal.pone.0342286","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pone.0342286","pdf_url":"https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0342286&type=printable","source":{"id":"https://openalex.org/S202381698","display_name":"PLoS ONE","issn_l":"1932-6203","issn":["1932-6203"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","erih-plus","jufo-1","ki-jl-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS One","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6303114295005798}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204147406.pdf","grobid_xml":"https://content.openalex.org/works/W7204147406.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W48332454","https://openalex.org/W650692540","https://openalex.org/W1602160603","https://openalex.org/W2037668591","https://openalex.org/W2078271269","https://openalex.org/W2115709314","https://openalex.org/W2119910794","https://openalex.org/W2130373985","https://openalex.org/W2146404132","https://openalex.org/W2296761362","https://openalex.org/W2297716127","https://openalex.org/W2553734051","https://openalex.org/W2762658547","https://openalex.org/W2769638259","https://openalex.org/W2809949684","https://openalex.org/W2898559532","https://openalex.org/W2909729347","https://openalex.org/W2913997948","https://openalex.org/W2996480032","https://openalex.org/W4399569497","https://openalex.org/W4400508677"],"related_works":[],"abstract_inverted_index":{"Closed-form":[0],"minimum":[1],"sample":[2,43,50,147],"size":[3,130,148],"criteria":[4],"for":[5,150,180],"developing":[6],"logistic":[7],"prediction":[8],"models,":[9],"such":[10,108],"as":[11,104,139],"the":[12,39,64,105,116,142,146],"Riley":[13],"framework":[14],"implemented":[15],"in":[16,170],"pmsampsize,":[17],"are":[18],"widely":[19],"used":[20],"but":[21,138],"may":[22],"become":[23],"optimistic":[24],"when":[25,197],"anticipated":[26],"discrimination":[27,90,140,199],"is":[28,115,200],"high.":[29],"We":[30,101],"conducted":[31],"a":[32,123,177],"Monte":[33],"Carlo":[34],"simulation":[35,191],"study":[36],"to":[37,98],"compare":[38],"formula-based":[40,187],"recommended":[41],"development":[42,60],"size,":[44,51],"nRiley,":[45],"with":[46,92,153,189],"an":[47],"empirical":[48],"required":[49,149],"nreq,":[52,137],"defined":[53,102],"by":[54],"out-of-sample":[55],"calibration-slope":[56],"stability":[57],"under":[58],"repeated":[59],"sampling.":[61],"Scenarios":[62],"fixed":[63,125],"candidate":[65],"parameter":[66],"dimension":[67],"at":[68,156,166],"p":[69],"=":[70],"10":[71],"and":[72,88,94,111,163,194],"crossed":[73],"predictor":[74],"distribution":[75],"(normal,":[76],"standardized":[77],"skewed":[78],"continuous,":[79],"binary),":[80],"signal":[81,95],"density":[82],"(dense":[83],"versus":[84],"sparse),":[85],"prevalence":[86],"(\u03d5\u2208{0.05,0.10,0.20}),":[87],"target":[89],"(AUCtarget\u2208{0.70,0.75,0.80,0.85,0.90}),":[91],"intercept":[93],"strength":[96],"calibrated":[97],"match":[99],"targets.":[100],"nreq":[103],"smallest":[106],"n":[107],"that":[109],"\ud835\udd3c(bn)\u22650.90":[110],"Pr(bn<0.80)\u22640.20,":[112],"where":[113],"bn":[114],"truth-based":[117],"logit-scale":[118],"calibration":[119,151],"slope":[120],"evaluated":[121],"on":[122],"large":[124,154],"validation":[126],"covariate":[127],"set":[128],"of":[129],"Nval=50,000.":[131],"At":[132],"moderate":[133],"discrimination,":[134],"nRiley":[135],"approximated":[136],"increased":[141],"formula":[143,181],"increasingly":[144],"underestimated":[145],"stability,":[152],"deficits":[155],"AUCtarget=0.90.":[157],"Separation-like":[158],"behavior":[159],"(extreme":[160],"fitted":[161],"risks":[162],"linear":[164],"predictors)":[165],"n=nRiley":[167],"became":[168],"common":[169],"high-discrimination":[171],"settings":[172],"despite":[173],"nominal":[174],"convergence,":[175],"providing":[176],"plausible":[178],"mechanism":[179],"optimism.":[182],"These":[183],"findings":[184],"support":[185],"augmenting":[186],"planning":[188],"targeted":[190],"stress":[192],"tests":[193],"instability":[195],"diagnostics":[196],"high":[198],"anticipated.":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2026-08-25T00:00:00"}