{"id":"https://openalex.org/W7202207360","doi":"https://doi.org/10.48550/arxiv.2608.09725","title":"Comparing Tobit and Two-Part Hurdle Models for Semi-Continuous Longitudinal Data with an Application to Clonal Hematopoiesis","display_name":"Comparing Tobit and Two-Part Hurdle Models for Semi-Continuous Longitudinal Data with an Application to Clonal Hematopoiesis","publication_year":2026,"publication_date":"2026-08-10","ids":{"openalex":"https://openalex.org/W7202207360","doi":"https://doi.org/10.48550/arxiv.2608.09725"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.09725","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.09725","pdf_url":"https://arxiv.org/pdf/2608.09725","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.09725","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5146529987","display_name":"Sumaja Bandreddi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4391012607","display_name":"Division of Cancer Epidemiology and Genetics","ror":"https://ror.org/00vkwep27","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210140884","https://openalex.org/I4391012607"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bandreddi, Sumaja","raw_affiliation_strings":["Biostatistics Branch , Division of Cancer Epidemiology and Genetics , National Cancer Institute , 9609 Medical Center Drive , Rockville , Maryland 20850 , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biostatistics Branch , Division of Cancer Epidemiology and Genetics , National Cancer Institute , 9609 Medical Center Drive , Rockville , Maryland 20850 , United States","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4391012607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146484988","display_name":"Pei Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4391012607","display_name":"Division of Cancer Epidemiology and Genetics","ror":"https://ror.org/00vkwep27","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210140884","https://openalex.org/I4391012607"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Pei","raw_affiliation_strings":["Biostatistics Branch , Division of Cancer Epidemiology and Genetics , National Cancer Institute , 9609 Medical Center Drive , Rockville , Maryland 20850 , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biostatistics Branch , Division of Cancer Epidemiology and Genetics , National Cancer Institute , 9609 Medical Center Drive , Rockville , Maryland 20850 , United States","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4391012607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062433098","display_name":"Rebecca L. Kelly","orcid":"https://orcid.org/0009-0009-4378-737X","observed_orcids":["https://orcid.org/0009-0009-4378-737X"]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4391012607","display_name":"Division of Cancer Epidemiology and Genetics","ror":"https://ror.org/00vkwep27","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210140884","https://openalex.org/I4391012607"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kelly, Rebecca L.","raw_affiliation_strings":["Integrative Tumor Epidemiology Branch , Division of Cancer Epidemiology and Genetics , National Cancer Institute , 9609 Medical Center Drive , Rockville , Maryland 20850 , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Integrative Tumor Epidemiology Branch , Division of Cancer Epidemiology and Genetics , National Cancer Institute , 9609 Medical Center Drive , Rockville , Maryland 20850 , United States","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4391012607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071089674","display_name":"Mitchell J. Machiela","orcid":"https://orcid.org/0000-0001-6538-9705","observed_orcids":["https://orcid.org/0000-0001-6538-9705"]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4391012607","display_name":"Division of Cancer Epidemiology and Genetics","ror":"https://ror.org/00vkwep27","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210140884","https://openalex.org/I4391012607"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Machiela, Mitchell J.","raw_affiliation_strings":["Integrative Tumor Epidemiology Branch , Division of Cancer Epidemiology and Genetics , National Cancer Institute , 9609 Medical Center Drive , Rockville , Maryland 20850 , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Integrative Tumor Epidemiology Branch , Division of Cancer Epidemiology and Genetics , National Cancer Institute , 9609 Medical Center Drive , Rockville , Maryland 20850 , United States","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4391012607"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039237147","display_name":"Paul S. Albert","orcid":"https://orcid.org/0000-0003-1658-1068","observed_orcids":["https://orcid.org/0000-0003-1658-1068"]},"institutions":[{"id":"https://openalex.org/I1299303238","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88","country_code":"US","type":"government","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238"]},{"id":"https://openalex.org/I4391012607","display_name":"Division of Cancer Epidemiology and Genetics","ror":"https://ror.org/00vkwep27","country_code":"US","type":"facility","lineage":["https://openalex.org/I1299022934","https://openalex.org/I1299303238","https://openalex.org/I4210140884","https://openalex.org/I4391012607"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Albert, Paul S.","raw_affiliation_strings":["Biostatistics Branch , Division of Cancer Epidemiology and Genetics , National Cancer Institute , 9609 Medical Center Drive , Rockville , Maryland 20850 , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biostatistics Branch , Division of Cancer Epidemiology and Genetics , National Cancer Institute , 9609 Medical Center Drive , Rockville , Maryland 20850 , United States","institution_ids":["https://openalex.org/I1299303238","https://openalex.org/I4391012607"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.9990000128746033,"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/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.9990000128746033,"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/T10968","display_name":"Statistical Distribution Estimation and Applications","score":0.00039999998989515007,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.00019999999494757503,"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/tobit-model","display_name":"Tobit model","score":0.9660000205039978},{"id":"https://openalex.org/keywords/model-equivalence","display_name":"model equivalence","score":0.7649999856948853},{"id":"https://openalex.org/keywords/clonal-hematopoiesis","display_name":"clonal hematopoiesis","score":0.871999979019165},{"id":"https://openalex.org/keywords/somatic-mosaicism","display_name":"somatic mosaicism","score":0.9660000205039978},{"id":"https://openalex.org/keywords/zero-inflation","display_name":"excess zeros","score":0.6759999990463257},{"id":"https://openalex.org/keywords/mixed-effects-models","display_name":"mixed models","score":0.4180000126361847},{"id":"https://openalex.org/keywords/model-selection","display_name":"model selection","score":0.3720000088214874}],"concepts":[{"id":"https://openalex.org/C166866094","wikidata":"https://www.wikidata.org/wiki/Q1307251","display_name":"Tobit model","level":2,"score":0.949999988079071},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.7455000281333923},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4968999922275543},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.48410001397132874},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44940000772476196},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4359000027179718},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.3569999933242798},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.35690000653266907},{"id":"https://openalex.org/C180075932","wikidata":"https://www.wikidata.org/wiki/Q5333342","display_name":"Econometric model","level":2,"score":0.3411000072956085},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C97379794","wikidata":"https://www.wikidata.org/wiki/Q4503892","display_name":"Censored regression model","level":3,"score":0.3000999987125397},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.29330000281333923},{"id":"https://openalex.org/C13985973","wikidata":"https://www.wikidata.org/wiki/Q6123589","display_name":"Truncated normal distribution","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C76969082","wikidata":"https://www.wikidata.org/wiki/Q486902","display_name":"Mathematical model","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.2728999853134155}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.09725","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.09725","pdf_url":"https://arxiv.org/pdf/2608.09725","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},{"id":"doi:10.48550/arxiv.2608.09725","doi":"https://doi.org/10.48550/arxiv.2608.09725","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.09725","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.09725","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.09725","pdf_url":"https://arxiv.org/pdf/2608.09725","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7202207360.pdf","grobid_xml":"https://content.openalex.org/works/W7202207360.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2150446996","https://openalex.org/W7108210678","https://openalex.org/W2133024404","https://openalex.org/W2110058119","https://openalex.org/W2522729423","https://openalex.org/W1993137559","https://openalex.org/W2744337429","https://openalex.org/W1982142871","https://openalex.org/W2271774748","https://openalex.org/W4393234858"],"abstract_inverted_index":{"Zero-inflated":[0],"nonnegative":[1],"continuous":[2,21,61,181],"longitudinal":[3,222],"data":[4,30,234],"frequently":[5],"arise":[6],"in":[7,272],"biomedical":[8],"studies":[9,273],"where":[10],"outcomes":[11,63],"consist":[12],"of":[13,16,34,68,121,160,218,274,280],"a":[14,44,52,118,255],"mixture":[15],"excess":[17,238],"zeros":[18],"and":[19,36,64,81,90,109,147,182,201,231,246],"positive":[20,62],"measurements.":[22],"Two":[23],"widely":[24],"used":[25,194],"approaches":[26],"for":[27,129,237,268],"analyzing":[28],"such":[29],"are":[31,107,163,198],"mixed-model":[32],"versions":[33],"Tobit":[35,42,113,151,162,190,245],"the":[37,56,60,65,104,112,122,126,130,142,150,154,158,161,180,189,205,216,227,244],"two-part":[38],"hurdle":[39,57,123,143,206,247],"models.":[40],"The":[41,71],"assumes":[43],"latent":[45],"regression":[46],"model":[47,83,124,166,191,207,258],"that":[48,111,141,188,259],"is":[49,133,144,167,208],"censored":[50],"below":[51],"specified":[53],"threshold,":[54],"while":[55,235],"separately":[58],"models":[59,75,106,213,248],"binary":[66,131,183],"indicator":[67],"being":[69],"positive.":[70],"choice":[72,84],"between":[73],"these":[74,196],"has":[76],"rarely":[77],"been":[78],"systematically":[79],"discussed,":[80],"inappropriate":[82],"may":[85],"lead":[86],"to":[87,169,214],"biased":[88],"estimation":[89],"misleading":[91],"scientific":[92],"interpretations.":[93],"In":[94],"this":[95,165],"paper,":[96],"we":[97,139],"derive":[98],"rigorous":[99],"mathematical":[100],"conditions":[101],"under":[102],"which":[103],"two":[105],"equivalent":[108],"show":[110],"can":[114],"be":[115,193],"viewed":[116],"as":[117],"special":[119],"case":[120],"when":[125,195],"link":[127],"function":[128],"process":[132],"probit.":[134],"Based":[135],"on":[136,178],"simulation":[137],"studies,":[138],"found":[140],"more":[145],"flexible":[146],"robust":[148],"than":[149],"model.":[152],"On":[153],"other":[155],"hand,":[156],"if":[157],"assumptions":[159,197],"met,":[164],"easier":[168],"interpret":[170],"since":[171],"it":[172],"does":[173],"not":[174],"require":[175],"distinct":[176],"inferences":[177],"both":[179,212],"processes.":[184],"We":[185,210],"therefore":[186],"recommend":[187],"only":[192],"scientifically":[199],"plausible":[200],"empirically":[202],"supported;":[203],"otherwise,":[204],"preferable.":[209],"applied":[211],"study":[215,233],"dynamics":[217],"somatic":[219],"mosaicism":[220],"using":[221],"clonal":[223,275],"fraction":[224],"measurements":[225],"from":[226,243,254],"Prostate,":[228],"Lung,":[229],"Colorectal,":[230],"Ovarian":[232],"accounting":[236],"zero":[239,261],"values.":[240],"Estimates":[241],"obtained":[242],"were":[249],"broadly":[250],"consistent":[251],"with":[252],"those":[253],"standard":[256],"linear":[257],"ignored":[260],"inflation.":[262],"These":[263],"findings":[264],"provide":[265],"additional":[266],"support":[267],"previously":[269],"reported":[270],"associations":[271],"hematopoiesis":[276],"across":[277],"different":[278],"types":[279],"mosaic":[281],"chromosomal":[282],"alterations.":[283]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-12T00:00:00"}
