Main Article Content
It has been well documented that ignoring measurement error may result in substantially biased estimates in many contexts including linear and nonlinear regressions. For survival data with measurement error in covariates, there has been extensive discussion in the literature with the focus typically centered on proportional hazards models. The impact of measurement error on inference under accelerated failure time models has received relatively little attention, although these models are very useful in survival data analysis. He et al. (2007) discussed accelerated failure time models with error-prone covariates and studied the bias induced by the naive approach of ignoring measurement error in covariates. To adjust for the effects of covariate measurement error, they described a simulation and extrapolation method. This method has theoretical advantages such as robustness to distributional assumptions for error prone covariates. Moreover, this method enjoys simplicity and flexibility for practical use. It is quite appealing to analysts who would like to accommodate covariate measurement error in their analysis. To implement this method, in this paper, we develop an R package for general users. Two data sets arising from clinical trials are employed to illustrate the use of the package.