Sample size calculation

To determine sample size, we assumed that 50% of cases would report a severe life event in the preceding 5 years, and that we would interview three controls for each case. To have 80% power to detect a difference between cases and controls at 5% significance, we needed 395 subjects if the odds ratio were 2, and 240 subjects if the odds ratio were 2.5.

Access jobs at BMJ Careers
Whats new online at Student BMJ