Table 3.

Example: design effects (DEs), total required study sizes (N), and number of clusters (k) required under each design given fixed total cluster sizes M and ICC (ρ)

Design constraints			CRT			CRT-BA			SW-CRT
M	ρ	t	DECRT	N	k	DEBA	N	k	DESW	N	k
30	0.01	2	1.29	1,017	34	2.24	1,766	59	3.22	2,538	85
30	0.25	2	8.25	6,501	217	2.75	2,167	73	3.23	2,544	85
100	0.01	9	1.99	1,569	16	2.64	2,084	21	2.16	1,702	18
100	0.25	9	25.75	20,291	203	2.92	2,298	23	2.25	1,772	18

Abbreviations: ICC, intracluster correlation coefficient; t, number of steps in the stepped wedge design; CRT, cluster randomized trial; CRT-BA, cluster randomized trial with before and after observations; SW-CRT, stepped wedge cluster randomized trial.

Example relates to a trial requiring 788 observations under individual randomization. Note that, N and k are rounded up to the nearest integer.