Inference for Parametric Regression Models

Abstract

In previous chapters, we focused on nonparametric methods for describing the survival experience of a population and regression models for survival data which do not require any specific distributional assumptions about the shape of the survival function. In this chapter, we shall discuss the use of parametric models for estimating univariate survival and for the censored-data regression problem. When these parametric models provide a good fit to data, they tend to give more precise estimates of the quantities of interest because these estimates are based on fewer parameters. Of course, if the parametric model is chosen incorrectly, it may lead to consistent estimators of the wrong quantity.