Predicting survival probabilities with semiparametric transformation models

Prediction of survival probabilities for future patients is one of the-main goals of fitting survival data with regression models. In this article we consider a large class of semiparametric transformation models, which includes the well-known proportional hazards and proportional odds models, for the analysis of failure time data. Specifically, we propose pointwise and simultaneous confidence interval procedures for the survival probability of future patients with specific covariates. These procedures can be easily implemented through;simulation and are illustrated with the data from two well-known clinical studies.