Skip to main content

Table 4 Statistical and clinical effects according to planned a priori sample size achievement

From: Rehabilitation interventions in randomized controlled trials for low back pain: proof of statistical significance often is not relevant

Scenario per n° of trials (total = 38a) N° of powered trials (%) N° of unpowered trials (%)
A) statistically significant and clinically relevant (n = 14) 7 (50) 7 (50)
B) statistically significant but not clinically relevant (n = 8) 1 (12) 7 (87)
C) not statistically significant but clinically relevant (n = 1) 0 1 (100)
D) not statistically significant and not clinically relevant (n = 15) 6 (40) 9 (60)
Totals 14 (37) 24 (63)
  1. aThe total number of trials is 38 because four studies did not report the patients number obtained from the sample size calculation (1 study belongs to scenario A, 2 belong to scenario B and 1 study belongs to scenario D)