Sample size requirements for a cluster randomised trial to reduce the average Edinburgh postnatal depression score from 8.5 to 7.5
|
Number in practice (m) |
Inflation factor (1 + (m − 1)ρ)) |
Total sample size required |
Number of practices |
| 10 | 1.26 | 1112 | 112 |
| 20 | 1.55 | 1367 | 68 |
| 30 | 1.84 | 1623 | 54 |
| 40 | 2.13 | 1879 | 47 |
| 50 | 2.42 | 2134 | 43 |
| 75 | 3.15 | 2778 | 37 |
| 100 | 3.87 | 3413 | 34 |
| 150 | 5.32 | 4692 | 32 |
| 200 | 6.77 | 5971 | 30 |
This assumes 80% power to detect a difference with a two tailed significance of 95%. The number required in a conventional randomised controlled trial is 441 patients/arm (882 in total).