A comparison of presmoothing methods in the estimation of transition probabilities

Abstract

One major goal in clinical applications of multi-state models is the estimation of transition probabilities. In a recent paper, landmark estimators were proposed to estimate these quantities, and their superiority with respect to the competing estimators has been proved in situations in which the Markov condition is violated. The idea behind their estimator is to use a procedure based on (differences between) Kaplan-Meier estimators derived from a subset of the data consisting of all subjects observed to be in the given state at the given time. Because of this, the computation of their estimator is performed in small sample sizes providing large standard errors in some circumstances. A valid approach is to consider a modification of the landmark estimator based on presmoothing. In this two presmoothing methods are compared. Simulation results indicate that both methods may be much more efficient than the unsmoothed estimator. Real data illustration is included.