Skip Navigation

Biometrika 2001 88(2):459-468; doi:10.1093/biomet/88.2.459
© 2001 by Biometrika Trust
This Article
Right arrow Full Text (PDF)
Right arrow Alert me when this article is cited
Right arrow Alert me if a correction is posted
Services
Right arrow Email this article to a friend
Right arrow Similar articles in this journal
Right arrow Alert me to new issues of the journal
Right arrow Add to My Personal Archive
Right arrow Download to citation manager
Right arrowRequest Permissions
Google Scholar
Right arrow Articles by Parner, E. T.
Right arrow Articles by Keiding, N.
Right arrow Search for Related Content
Social Bookmarking
Add to CiteULike   Add to Connotea   Add to Del.icio.us  
What's this?

Misspecified proportional hazard models and confirmatory analysis of survival data

Erik T.Parner1 and Niels Keiding2

1 Department of Biostatistics, University of Aarhus, Vennelyst Boulevard 6, DK-8000 Aarhus C, Denmarkparner{at}biostat.au.dk 2 Department of Biostatistics, University of Copenhagen, Blegdamsvej 3, DK-2200 Copenhagen N, Denmark.n.keiding{at}biostat.ku.dk

In survival analysis of follow-up studies with staggered entry, it may be requested to examine a chance finding at an interim analysis in a confirmatory analysis based on ‘independent evidence’.Keiding et al. (1987) suggested incorporating residual lifetimes of initial survivors into the confirmatory analysis and indicated heuristically that this provides valid independent evidence, assuming that the statistical model is true. The present paper provides a full mathematical proof of a much more robust result, namely that the re-use of original survivors provides an asymptotically independent confirmatory analysis even under a broad class of model misspecification, allowing unmeasured patient heterogeneity.

Key Words: Confirmatory analysis; Empirical process; Interim analysis; Misspecification; Proportional hazard regression

Received November 1999. Revised November 2000


Add to CiteULike CiteULike   Add to Connotea Connotea   Add to Del.icio.us Del.icio.us    What's this?




Disclaimer:
Please note that abstracts for content published before 1996 were created through digital scanning and may therefore not exactly replicate the text of the original print issues. All efforts have been made to ensure accuracy, but the Publisher will not be held responsible for any remaining inaccuracies. If you require any further clarification, please contact our Customer Services Department.