Selection between proportional and stratified hazards models based on expected log-likelihood

Abstract : The problem of selecting between semi-parametric and proportional hazards models is considered. We propose to make this choice based on the expectation of the log-likelihood (ELL) which can be estimated by the likelihood cross-validation (LCV) criterion. The criterion is used to choose an estimator in families of semi-parametric estimators defined by the penalized likelihood. A simulation study shows that the ELL criterion performs nearly as well in this problem as the optimal Kullback-Leibler criterion in term of Kullback-Leibler distance and that LCV performs reasonably well. The approach is applied to a model of age-specific risk of dementia as a function of sex and educational level from the data of a large cohort study.
Document type :
Journal articles
Complete list of metadatas

Cited literature [21 references]  Display  Hide  Download

https://www.hal.inserm.fr/inserm-00366565
Contributor : Evelyne Mouillet <>
Submitted on : Monday, March 9, 2009 - 9:40:52 AM
Last modification on : Friday, April 19, 2019 - 9:40:02 AM
Long-term archiving on : Tuesday, June 8, 2010 - 9:24:31 PM

Files

liquet_commenges_saracco_2007....
Files produced by the author(s)

Identifiers

Collections

Citation

Benoit Liquet, Jérôme Saracco, Daniel Commenges. Selection between proportional and stratified hazards models based on expected log-likelihood. Computational Statistics, Springer Verlag, 2007, 22 (4), pp.619-634. ⟨10.1007/s00180-007-0079-3⟩. ⟨inserm-00366565⟩

Share

Metrics

Record views

305

Files downloads

1141