Parameter orthogonality in mixed regression models for survival data

dc.contributor.authorHutton, J.
dc.contributor.authorSolomon, P.
dc.date.issued1997
dc.description.abstractThe implications of parameter orthogonality for the robustness of survival regression models are considered. The question of which of the proportional hazards or the accelerated life families of models would be more appropriate for analysis is usually ignored, and the proportional hazards family is applied, particularly in medicine, for convenience. Accelerated life models have conventionally been used in reliability applications. We propose a one-parameter family mixture survival model which includes both the accelerated life and the proportional hazards models. By orthogonalizing relative to the mixture parameter, we can show that, for small effects of the covariates, the regression parameters under the alternative families agree to within a constant. This recovers a known misspecification result. We use notions of parameter orthogonality to explore robustness to other types of misspecification including misspecified base-line hazards. The results hold in the presence of censoring. We also study the important question of when proportionality matters.
dc.description.statementofresponsibilityJ. L. Hutton and P. J. Solomon
dc.identifier.citationJournal of the Royal Statistical Society Series B: Statistical Methodology, 1997; 59(1):125-136
dc.identifier.doi10.1111/1467-9868.00058
dc.identifier.issn1467-9868
dc.identifier.issn1467-9868
dc.identifier.orcidSolomon, P. [0000-0002-0667-6947]
dc.identifier.urihttp://hdl.handle.net/2440/5151
dc.language.isoen
dc.publisherRoyal Statistical Society
dc.rights© 1997 Royal Statistical Society
dc.source.urihttps://doi.org/10.1111/1467-9868.00058
dc.subjectAccelerated life; misspecification; mixture models; parameter orthogonality; proportional hazards; robustness; survival data
dc.titleParameter orthogonality in mixed regression models for survival data
dc.typeJournal article
pubs.publication-statusPublished

Files