Nonparametric Inference in Additive Risk Models for Counting Processes.

Abstract : Nonparametric estimators for the hazard functions in an additive risk model for counting process are studied. This document establishes a functional central limit theorem for the integrated estimators and show how this can be used to find the asymptotic null distribution of a maximal deviation statistic for Kolmogorov-Smirnov type testing. In addition, the author provides confidence bands f or approximations to the integrated hazard functions and show that certain smoothed versions of the hazard function estimators are uniformly consistent. Keywords: Martingale methods; Regression models. (Author)