Related Experiment Video
Updated: Oct 9, 2026

An R-Based Landscape Validation of a Competing Risk Model
Published on: September 16, 2022
Nonparametric tests for stratum effects in the Cox model
1Department of Statistics, University of Missouri, 222 Math Sciences Building, Columbia, MO 65211, USA. tsun@stat.missouri.edu
Abstract:
This paper considers the stratified proportional hazards model with a focus on the assessment of stratum effects. The assessment of such effects is often of interest, for example, in clinical trials. In this case, two relevant tests are the test of stratum interaction with covariates and the test of stratum interaction with baseline hazard functions. For the test of stratum interaction with covariates, one can use the partial likelihood method (Kalbfleisch and Prentice, 1980; Lin, 1994). For the test of stratum interaction with baseline hazard functions, however, there seems to be no formal test available. We consider this problem and propose a class of nonparametric tests. The asymptotic distributions of the tests are derived using the martingale theory. The proposed tests can also be used for survival comparisons which need to be adjusted for covariate effects. The method is illustrated with data from a lung cancer clinical trial.
Related Concept Videos
The Mantel-Cox Log-Rank Test
Comparing the Survival Analysis of Two or More Groups
Friedman Two-way Analysis of Variance by Ranks
Test for Homogeneity
Assumptions of Survival Analysis
Stratified Sampling Method
To choose a stratified sample, divide the population into groups called strata and then take a...

