Optimal designs for full and partial likelihood information - with application to survival models
Optimal designs for full and partial likelihood information - with application to survival models
Time-to-event data are often modelled through Cox's proportional hazards model for which inference is based on the partial likelihood function. We derive a general expression for the asymptotic covariance matrix of Cox's partial likelihood estimator for the covariate coefficients. Our approach is illustrated through an application to the special case of only one covariate, for which we construct minimum variance designs for different censoring mechanisms and both binary and interval design spaces. We compare these designs with the corresponding ones found using the full likelihood approach and demonstrate that the latter designs are highly efficient also for partial likelihood estimation.
right-censoring, cox's proportional hazards model, optimal design, full likelihood, partial likelihood
27–37
Konstantinou, Maria
242713ea-332c-466d-82e5-b2d6aa8dad07
Biedermann, S.
fe3027d2-13c3-4d9a-bfef-bcc7c6415039
Kimber, Alan C.
40ba3a19-bbe3-47b6-9a8d-68ebf4cea774
1 October 2015
Konstantinou, Maria
242713ea-332c-466d-82e5-b2d6aa8dad07
Biedermann, S.
fe3027d2-13c3-4d9a-bfef-bcc7c6415039
Kimber, Alan C.
40ba3a19-bbe3-47b6-9a8d-68ebf4cea774
Konstantinou, Maria, Biedermann, S. and Kimber, Alan C.
(2015)
Optimal designs for full and partial likelihood information - with application to survival models.
Journal of Statistical Planning and Inference, 165, .
(doi:10.1016/j.jspi.2015.03.007).
Abstract
Time-to-event data are often modelled through Cox's proportional hazards model for which inference is based on the partial likelihood function. We derive a general expression for the asymptotic covariance matrix of Cox's partial likelihood estimator for the covariate coefficients. Our approach is illustrated through an application to the special case of only one covariate, for which we construct minimum variance designs for different censoring mechanisms and both binary and interval design spaces. We compare these designs with the corresponding ones found using the full likelihood approach and demonstrate that the latter designs are highly efficient also for partial likelihood estimation.
Text
coxmodel for eprints.pdf
- Accepted Manuscript
More information
Accepted/In Press date: 14 March 2015
e-pub ahead of print date: 2 April 2015
Published date: 1 October 2015
Additional Information:
Published in the October 2015 volume
Keywords:
right-censoring, cox's proportional hazards model, optimal design, full likelihood, partial likelihood
Organisations:
Statistical Sciences Research Institute
Identifiers
Local EPrints ID: 366672
URI: http://eprints.soton.ac.uk/id/eprint/366672
ISSN: 0378-3758
PURE UUID: 834e67f1-cd3f-4d51-a951-31cae7f314e6
Catalogue record
Date deposited: 04 Jul 2014 15:47
Last modified: 15 Mar 2024 03:26
Export record
Altmetrics
Contributors
Author:
Maria Konstantinou
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
