Table 1 Power (probability of detecting a true effect %) under a range of baseline proportions of parental awareness of the health risk of their child’s weight using a matched case–control design with a two sided alpha of 5% (calculations carried out using the sampsi_mcc command in STATA v10)
Sample size | Effect size | Power (if 30% recognise health risk at baseline) | Power (if 10% recognise health risk at baseline) |
|---|---|---|---|
200 | 5% | 28 | 58 |
400 | 5% | 50 | 91 |
800 | 5% | 80 | 100 |