Additive mean residual life model with covariate measurement errors

In this paper, we consider the additive mean residual life model when a proportion of covariates cannot be observed accurately but repeated measurements on covariates are available. The number of repeated measurements is allowed to vary across different subjects. A nonparametric-correction method is developed for inference about regression parameters and the baseline mean residual life function. The resultant estimators are shown to be consistent and asymptotically normal, and consistent standard error estimators are also provided. Simulation studies are carried out to examine the performance of the proposed approach. We illustrate the method by application to data from an HIV clinical trial.