. Author manuscript; available in PMC: 2010 Sep 1.

Published in final edited form as: Hum Ecol Risk Assess. 2009 Sep 1;15(5):858–875. doi: 10.1080/10807030903153360

Table 5.

Statistical power comparisons of trend tests on four doses (0,0.5,1.0 and 2.0) and n = 50 per group based on 2000 simulated data sets, where CA: Cochran-Armitage trend test, Logit: Dinse-Lagakos logistic regression score test, Poly-k: survival adjusted test by Bailer and Portier (1988); β₁ is effect of dose on tumor incidence or mortality due to tumor; β₂ is effect of dose on mortality due to competing risk or non-tumor related death (for common tumor).

						Poly-k
Tumor	η ₁	(β₁,β₂)	CA	logrank	logit	k = 1.5	k = 3	k = 6
Cause of death	1.5	(0.4,0.0)	.749	.791	.366	.657	.522	.282
		(0.7,0.0)	.998	1.00	.768	.995	.985	.862
		(0.4,0.7)	.221	.695	.242	.457	.638	.734
		(0.7,0.7)	.896	.997	.052	.975	.988	.975
	3.0	(0.4,0.0)	.671	.795	.478	.617	.505	.275
		(0.7,0.0)	.992	.999	.889	.988	.978	.863
		(0.4,0.7)	.051	.600	.256	.087	.200	.314
		(0.7,0.7)	.356	.984	.047	.641	.792	.816
	6.0	(0.4,0.0)	.486	.754	.544	.452	.394	.234
		(0.7,0.0)	.900	.999	.929	.903	.881	.736
		(0.4,0.7)	.405	.440	.185	.099	.020	.017
		(0.7,0.7)	.089	1.00	.085	.024	.040	.051
Tumor						Poly-k
Incidental	η ₁	(β₁,β₂)	CA	logrank	logit	k = 1.5	k = 3	k = 6
	1.5	(0.4,0.0)	.749	.512	.756	.641	.487	.188
		(0.7,0.0)	.998	.913	.999	.995	.979	.739
		(0.4,0.7)	.221	.999	.611	.446	.605	.609
		(0.7,0.7)	.896	1.00	.986	.972	.983	.931
	3.0	(0.4,0.0)	.671	.464	.743	.586	.436	.137
		(0.7,0.0)	.992	.865	.998	.987	.958	.639
		(0.4,0.7)	.051	.999	.534	.080	.173	.208
		(0.7,0.7)	.356	1.00	.958	.621	.732	.630
	6.0	(0.4,0.0)	.486	.353	.645	.410	.268	.044
		(0.7,0.0)	.896	.671	.984	.878	.776	.280
		(0.4,0.7)	.401	.980	.376	.090	.013	.005
		(0.7,0.7)	.089	.917	.044	.027	.070	.165