Testing the proportional hazards assumption in case-cohort analysis

Table 2 Proportion of simulations (out of 1000) with P-values < 0.05 for one continuous variable and one binary variable

Proportionality	Variable	Corr with time	Corr with rank	Corr with KM estimate
Proportionality for both variables	Continuous	0.059	0.056	0.056
Proportionality for both variables	Binary	0.042	0.043	0.045
Proportionality for the continuous but not the binary variable	Continuous	0.047	0.048	0.045
	Binary	0.646	0.641	0.647
Proportionality for the binary but not the continuous variable	Continuous	0.979	0.971	0.967
	Binary	0.043	0.045	0.045
Non-proportionality for both variables	Continuous	0.994	0.991	0.989
	Binary	0.597	0.586	0.580

ISSN: 1471-2288