Clustering of continuous and binary outcomes at the general practice level in individually randomised studies in primary care - a review of 10 years of primary care trials

Table 5 Sample size required for various values of ICC and S

Balance of treatment arms within practices	S = 0 Perfectly balanced	S = 0.75 Slightly unbalanced	S = 2 Unbalanced
Design effect	0.99	0.9975	1.01
Trial size
150	149	150	152
300	297	299	303
500	495	499	505
1000	990	998	1010
Design effect	0.9	0.975	1.1
Trial size
150	135	146	165
300	270	293	330
500	450	489	550
1000	900	975	1100

ISSN: 1471-2288