A simulation-extrapolation approach for the mixture cure model with mismeasured covariates

We consider survival data from a population with cured subjects in the presence of mismeasured covariates. use mixture cure model to account for individuals that will never experience event and at same time distinguish between effect covariates on probabilities times. In particular, practical applications, it seems interest assume logistic form incidence Cox proportional hazards latency. To correct estimators bias introduced by measurement error, we simex algorithm, which is very general simulation based method. It essentially estimates this introducing additional error then recovers corrected through an extrapolation approach. The are shown be consistent asymptotically normally distributed when true function known. investigate their finite sample performance study apply proposed method analyse prostate specific antigen (PSA) patients cancer.