Skip to main content
. 2014 Jan 21;9(1):e85949. doi: 10.1371/journal.pone.0085949

Table 4. Standardized percentage difference per subgroup for RCTs where recalculation of the sample sizes was feasible (n = 121).

Standardized difference
Subgroup Recalculated>actual* n = 35 Recalculated<actual** n = 84 Recalculated = actual n = 2
median −30.00 23.60 0.00
min −237.50 1.60 0.00
max −1.70 84.20 0.00
IQR 53.35 22.58 0.00

*Recalculated > actual indicates underestimation of the sample size by the authors of the RCTs and is characterized by negative values for the calculated standardized difference.

**Recalculated < actual indicates overestimation of the sample size by the authors of the RCTs and is characterized by positive values for the calculated standardized difference.