Show simple item record

AuthorZimmermann, Georgdc.contributor.author
AuthorPauly, Markusdc.contributor.author
AuthorBathke, Arne C.dc.contributor.author
Date of accession2023-01-24T17:16:51Zdc.date.accessioned
Available in OPARU since2023-01-24T17:16:51Zdc.date.available
Date of first publication2019-01-02dc.date.issued
AbstractIt is well known that the standard F test is severely affected by heteroskedasticity in unbalanced analysis of covariance models. Currently available potential remedies for such a scenario are based on heteroskedasticity-consistent covariance matrix estimation (HCCME). However, the HCCME approach tends to be liberal in small samples. Therefore, in the present paper, we propose a combination of HCCME and a wild bootstrap technique, with the aim of improving the small-sample performance. We precisely state a set of assumptions for the general analysis of covariance model and discuss their practical interpretation in detail, since this issue may have been somewhat neglected in applied research so far. We prove that these assumptions are sufficient to ensure the asymptotic validity of the combined HCCME-wild bootstrap analysis of covariance. The results of our simulation study indicate that our proposed test remedies the problems of the analysis of covariance F test and its heteroskedasticity-consistent alternatives in small to moderate sample size scenarios. Our test only requires very mild conditions, thus being applicable in a broad range of real-life settings, as illustrated by the detailed discussion of a dataset from preclinical research on spinal cord injury. Our proposed method is ready-to-use and allows for valid hypothesis testing in frequently encountered settings (e.g., comparing group means while adjusting for baseline measurements in a randomized controlled clinical trial).dc.description.abstract
Languageendc.language.iso
PublisherUniversität Ulmdc.publisher
LicenseCC BY-NC-ND 4.0 Internationaldc.rights
Link to license texthttps://creativecommons.org/licenses/by-nc-nd/4.0/dc.rights.uri
KeywordHeteroskedasticity-consistent covariance matrix estimatordc.subject
Keywordsmall sampledc.subject
Keywordwild bootstrapdc.subject
KeywordRANDOMIZED CLINICAL-TRIALSdc.subject
KeywordSPINAL-CORD-INJURYdc.subject
KeywordREGRESSIONdc.subject
KeywordADJUSTMENTdc.subject
KeywordANCOVAdc.subject
KeywordESTIMATORSdc.subject
KeywordPARAMETERSdc.subject
Dewey Decimal GroupDDC 500 / Natural sciences & mathematicsdc.subject.ddc
Dewey Decimal GroupDDC 510 / Mathematicsdc.subject.ddc
Dewey Decimal GroupDDC 610 / Medicine & healthdc.subject.ddc
LCSHAnalysis of covariancedc.subject.lcsh
LCSHRare diseasesdc.subject.lcsh
LCSHResampling (Statistics)dc.subject.lcsh
LCSHClinical trialsdc.subject.lcsh
LCSHRegression analysisdc.subject.lcsh
LCSHLinedc.subject.lcsh
TitleSmall-sample performance and underlying assumptions of a bootstrap-based inference method for a general analysis of covariance model with possibly heteroskedastic and nonnormal errorsdc.title
Resource typeWissenschaftlicher Artikeldc.type
SWORD Date2020-12-09T19:40:11Zdc.date.updated
VersionpublishedVersiondc.description.version
DOIhttp://dx.doi.org/10.18725/OPARU-46825dc.identifier.doi
URNhttp://nbn-resolving.de/urn:nbn:de:bsz:289-oparu-46901-2dc.identifier.urn
GNDHeteroskedastizitätdc.subject.gnd
GNDKovarianzanalysedc.subject.gnd
GNDSeltene Krankheitdc.subject.gnd
GNDRegressionsanalysedc.subject.gnd
GNDSchätzfunktiondc.subject.gnd
GNDLiniedc.subject.gnd
FacultyFakultät für Mathematik und Wirtschaftswissenschaftenuulm.affiliationGeneral
InstitutionInstitut für Statistikuulm.affiliationSpecific
Peer reviewjauulm.peerReview
DCMI TypeTextuulm.typeDCMI
CategoryPublikationenuulm.category
DOI of original publication10.1177/0962280218817796dc.relation1.doi
Source - Title of sourceStatistical Methods in Medical Researchsource.title
Source - Place of publicationSAGE Publicationssource.publisher
Source - Volume28source.volume
Source - Issue12source.issue
Source - Year2019source.year
Source - From page3808source.fromPage
Source - To page3821source.toPage
Source - ISSN0962-2802source.identifier.issn
Source - eISSN1477-0334source.identifier.eissn
WoS000486890500021uulm.identifier.wos
Bibliographyuulmuulm.bibliographie
DFG project uulmInferenzmethoden für multivariate und hochdimensionale Daten / DFG / 282140603 [PA 2409/4-1]uulm.projectDFG


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record