A ROBUST METHOD FOR PROPORTIONAL HAZARDS REGRESSION

✍ Scribed by C. E. MINDER; T. BEDNARSKI

• Publisher: John Wiley and Sons
• Year: 1996
• Tongue: English
• Weight: 785 KB
• Volume: 15
• Category: Article
• ISSN: 0277-6715
• DOI: 10.1002/(sici)1097-0258(19960530)15:10<1033::aid-sim215>3.0.co;2-y

✦ Synopsis

In this paper we give an informal introduction to a robust method for survival analysis which is based on a modification of the usual partial likelihood estimator (PLE). Large sample results lead us to expect reduced bias for this robust estimator compared with the PLE whenever there are even slight violations of the model. In this paper we investigate three types of violation: (a) varying dependency structure of survival time and covariates over the sample; (b) omission of influential covariates, and (c) errors in the covariates. The simulations presented support the above expectation. Analyses of data sets from cancer epidemiology and from a clinical trial in lung cancer illustrate that a better fit and additional insights may be gained using robust estimators.

A. subgroups of patients responding differently to covariate combinations; B. covariates missing from the model; C. covariates misclassified or measured imprecisely.

Depending on the extent of the deviation and on the purpose of the analysis, it may be justified to use the proportional hazards model in such situations, provided robust estimators are being