# Chapter 2 Kaplan Meier estimator

Once we have explained what is the survival curve and other introductory questions, we move on the estimation. Note that we can estimate the survival (or hazard) function in two ways:

• by specifying a parametric model for $$\lambda(t)$$ based on a particular density function $$f(t)$$ (parametric estimation)

• by developing an empirical estimate of the survival function (i.e., nonparametric estimation)

This Chapter describes how to plot and interpret survival data using the Kaplan-Meier (KM) estimator (nonparametric) and how to test whether or not two or more KM curves are equivalent using the log–rank test. Alternative tests to the log–rank test are also described. Furthermore, methods for computing $$(1-\alpha)$$% confidence intervals for a KM curve are afforded.