TITLE:
Survival Model Inference Using Functions of Brownian Motion
AUTHORS:
John O’Quigley
KEYWORDS:
Brownian Motion; Brownian Bridge; Cox Model; Integrated Brownian Motion; Kaplan-Meier Estimate; Non-Proportional Hazards; Reflected Brownian Motion; Time-Varying Effects; Weighted Score Equation
JOURNAL NAME:
Applied Mathematics,
Vol.3 No.6,
June
27,
2012
ABSTRACT: A family of tests for the presence of regression effect under proportional and non-proportional hazards models is described. The non-proportional hazards model, although not completely general, is very broad and includes a large number of possibilities. In the absence of restrictions, the regression coefficient, β(t), can be any real function of time. When β(t) = β, we recover the proportional hazards model which can then be taken as a special case of a non-proportional hazards model. We study tests of the null hypothesis; H0:β(t) = 0 for all t against alternatives such as; H1:∫β(t)dF(t) ≠ 0 or H1:β(t) ≠ 0 for some t. In contrast to now classical approaches based on partial likelihood and martingale theory, the development here is based on Brownian motion, Donsker’s theorem and theorems from O’Quigley [1] and Xu and O’Quigley [2]. The usual partial likelihood score test arises as a special case. Large sample theory follows without special arguments, such as the martingale central limit theorem, and is relatively straightforward.