The Direct Assignment Option as a Modular Design Component: An Example for the Setting of Two Predefined Subgroups

Table 2

Sample size calculations for 1-sided and , for different treatment effects in the two subgroups. RR_trt is the response rate in the treatment group, RR_control is the response rate in the control group, and RRR_trt:control is the ratio of response rates in the treatment versus control groups (i.e., treatment effect).

Case	M+ subgroup			M− subgroup
	Treatment effect, RRRtrt:control	RRtrt/RRcontrol		Treatment effect, RRRtrt:control	RRtrt/RRcontrol
I (no interaction)	2	0.4/0.2	65	2	0.4/0.2	65
II (interaction)	2	0.4/0.2	65	0.5 (i.e., reverse benefit)	0.1/0.2	161