Comparing survival curves based on medians

Table 6 The empirical powers of the tests at the significance level 0.05 when the survival times have uniform, exponential, log-normal,uniform and exponential, uniform and log-normal, or exponential and log-normal distributions with unequal medians and sample sizes n ₁ = 20, n ₂ = 25, n ₃ = 25, n ₄ = 30

Distributions and parameters	Censoring rate	BC	TJ	New
Uniform distribution θ = (10,10,10.5,10) a = (4,4,4,4) c = (2,2,2,2)	0	0.169	0.133	0.140
	0.1	0.171	0.153	0.126
	0.2	0.175	0.186	0.117
	0.3	0.177	0.216	0.104
Exponential distribution θ = (10,10,10,10) a = (0.1,0.15,0.15,0.1)	0	0.229	0.184	0.196
	0.1	0.233	0.199	0.201
	0.2	0.233	0.218	0.187
	0.3	0.221	0.231	0.160
Log-normal distribution θ = (log(10), log(14), log(14), log(10)) a = (1,1,1,1)	0	0.231	0.185	0.201
	0.1	0.212	0.190	0.169
	0.2	0.210	0.218	0.163
	0.3	0.201	0.240	0.140
Two uniform and two exponential distributions θ = (10,13,13-10log(2),10-10log(2)) a = (0.1,0.1,0.1,0.1) c = (0.01,0.01,0.01,0.01)	0	0.277	0.229	0.234
	0.1	0.266	0.270	0.190
	0.2	0.264	0.295	0.172
	0.3	0.258	0.315	0.158
Two uniform and two log-normal distributions θ = (10,12,2.5,2.5) a = (1,1,1,1) c = (0.2,0.2,0.2,0.2)	0	0.288	0.218	0.275
	0.1	0.250	0.257	0.240
	0.2	0.249	0.294	0.218
	0.3	0.253	0.329	0.197
Two log-normal and two exponential distributions θ = (log(10),log(13),13-10log(2),10-10log(2)), a = (1,1,0.1,0.1)	0	0.229	0.183	0.182
	0.1	0.223	0.195	0.174
	0.2	0.228	0.217	0.168
	0.3	0.220	0.242	0.147

ISSN: 1471-2288