Please use this identifier to cite or link to this item: https://doi.org/10.1177/0962280219837656
DC FieldValue
dc.titleHandling ties in continuous outcomes for confounder adjustment with rank-ordered logit and its application to ordinal outcomes
dc.contributor.authorNing, Yilin
dc.contributor.authorTan, Chuen Seng
dc.contributor.authorMaraki, Angeliki
dc.contributor.authorHo, Peh Joo
dc.contributor.authorHodgins, Sheilagh
dc.contributor.authorComasco, Erika
dc.contributor.authorNilsson, Kent W
dc.contributor.authorWagner, Philippe
dc.contributor.authorKhoo, Eric YH
dc.contributor.authorTai, E-Shyong
dc.contributor.authorKao, Shih Ling
dc.contributor.authorHartman, Mikael
dc.contributor.authorReilly, Marie
dc.contributor.authorStoer, Nathalie C
dc.date.accessioned2021-12-01T12:40:56Z
dc.date.available2021-12-01T12:40:56Z
dc.date.issued2020-02-01
dc.identifier.citationNing, Yilin, Tan, Chuen Seng, Maraki, Angeliki, Ho, Peh Joo, Hodgins, Sheilagh, Comasco, Erika, Nilsson, Kent W, Wagner, Philippe, Khoo, Eric YH, Tai, E-Shyong, Kao, Shih Ling, Hartman, Mikael, Reilly, Marie, Stoer, Nathalie C (2020-02-01). Handling ties in continuous outcomes for confounder adjustment with rank-ordered logit and its application to ordinal outcomes. STATISTICAL METHODS IN MEDICAL RESEARCH 29 (2) : 437-454. ScholarBank@NUS Repository. https://doi.org/10.1177/0962280219837656
dc.identifier.issn09622802
dc.identifier.issn14770334
dc.identifier.urihttps://scholarbank.nus.edu.sg/handle/10635/209055
dc.description.abstractThe rank-ordered logit (rologit) model was recently introduced as a robust approach for analysing continuous outcomes, with the linear exposure effect estimated by scaling the rank-based log-odds estimate. Here we extend the application of the rologit model to continuous outcomes with ties and ordinal outcomes treated as imperfectly-observed continuous outcomes. By identifying the functional relationship between survival times and continuous outcomes, we explicitly establish the equivalence between the rologit and Cox models to justify the use of the Breslow, Efron and perturbation methods in the analysis of continuous outcomes with ties. Using simulation, we found all three methods perform well with few ties. Although an increasing extent of ties increased the bias of the log-odds and linear effect estimates and resulted in reduced power, which was somewhat worse when the model was mis-specified, the perturbation method maintained a type I error around 5%, while the Efron method became conservative with heavy ties but outperformed Breslow. In general, the perturbation method had the highest power, followed by the Efron and then the Breslow method. We applied our approach to three real-life datasets, demonstrating a seamless analytical workflow that uses stratification for confounder adjustment in studies of continuous and ordinal outcomes.
dc.language.isoen
dc.publisherSAGE PUBLICATIONS LTD
dc.sourceElements
dc.subjectScience & Technology
dc.subjectLife Sciences & Biomedicine
dc.subjectPhysical Sciences
dc.subjectHealth Care Sciences & Services
dc.subjectMathematical & Computational Biology
dc.subjectMedical Informatics
dc.subjectStatistics & Probability
dc.subjectMathematics
dc.subjectRank-ordered logit model
dc.subjectstratification
dc.subjecttied observations
dc.subjectcontinuous outcome
dc.subjectordinal outcome
dc.subjectQUALITY-OF-LIFE
dc.subjectREGRESSION-MODELS
dc.subjectEFFICIENCY
dc.subjectSMOKING
dc.subjectTIMES
dc.typeArticle
dc.date.updated2021-11-30T17:02:29Z
dc.contributor.departmentDEPT OF MEDICINE
dc.contributor.departmentEPIDEMIOLOGY & PUBLIC HEALTH
dc.contributor.departmentSAW SWEE HOCK SCHOOL OF PUBLIC HEALTH
dc.description.doi10.1177/0962280219837656
dc.description.sourcetitleSTATISTICAL METHODS IN MEDICAL RESEARCH
dc.description.volume29
dc.description.issue2
dc.description.page437-454
dc.published.statePublished
Appears in Collections:Staff Publications
Elements

Show simple item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
Handling ties in continuous outcomes for confounder adjustment with rank-ordered logit and its application to ordinal outcomes.pdfPublished version734.18 kBAdobe PDF

CLOSED

None

SCOPUSTM   
Citations

2
checked on Dec 3, 2022

Page view(s)

104
checked on Dec 1, 2022

Download(s)

1
checked on Dec 1, 2022

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.