ABSTRACT
This chapter discusses the analysis of population-based cancer survival data with cure models. It describes the population-based cancer registry and survival data, which has different structures and features from the survival data in clinical trials. The chapter also discusses the popular parametric cure models for analyzing the population-based cancer survival data and describes the implementation of several R packages. The measure of net survival is not influenced by changes in mortality from other causes and, therefore, provides a useful measure for cancer survival trends across time, and comparisons between racial-ethnic groups or between registries. By forcing the log cumulative excess hazard in the flexible parametric survival model to not only be linear but also to have zero slope after the last knot, the model explicitly allows the estimation of cure rate. The chapter examines a minimum version of a one-sample log-rank test for testing the non-inferiority of survival.
