Inference in the presence of likelihood monotonicity for proportional hazards regression

Proportional hazards are often used to model event time data subject to censoring. Samples involving discrete covariates with strong effects can lead to infinite maximum partial likelihood estimates. A methodology is presented for eliminating nuisance parameters estimated at infinity using approxima...

Full description

Saved in:
Bibliographic Details
Published inStatistica Neerlandica Vol. 77; no. 3; pp. 322 - 339
Main Authors Kolassa, John E., Zhang, Juan
Format Journal Article
LanguageEnglish
Published Oxford Blackwell Publishing Ltd 01.08.2023
Subjects
conditional inference
Hazards
Inference
Infinity
likelihood monotonicity
Parameter estimation
proportional hazards regression
Online AccessGet full text
ISSN0039-0402
1467-9574
DOI10.1111/stan.12287

Cover

More Information
Summary:Proportional hazards are often used to model event time data subject to censoring. Samples involving discrete covariates with strong effects can lead to infinite maximum partial likelihood estimates. A methodology is presented for eliminating nuisance parameters estimated at infinity using approximate conditional inference. Of primary interest is testing in cases in which the parameter of primary interest has a finite estimate, but in which other parameters are estimated at infinity.
Bibliography:Funding information
United States National Science Foundation
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0039-0402
1467-9574
DOI:10.1111/stan.12287