Skip to main content

Table 4 Possible design effect for a continuous outcome based upon database

From: Clustering in surgical trials - database of intracluster correlations

Outcome ICC† Average cluster size Design effectχ
     expertise-based design stratified design
EQ-5D 12 m 0.01 min(centre)* 9.4 1.08 0.99
  0.01 median(centre)* 32.4 1.31 0.99
  0.01 max(centre)* 51.1 1.50 0.99
  0.01 median adj.(centre)‡ 64.4 1.63 0.99
  0.01 min(surgeon)* 2.8 1.02 0.99
  0.01 median(surgeon)* 6.1 1.05 0.99
  0.01 max(surgeon)* 29.9 1.29 0.99
  0.01 median adj.(surgeon)‡ 35.3 1.34 0.99
Operation time 0.27 min(centre)* 9.4 3.27 0.73
  0.27 median(centre)* 32.4 9.48 0.73
  0.27 max(centre)* 51.1 14.53 0.73
  0.27 median adj.(centre)‡ 64.4 18.12 0.73
  0.27 min(surgeon)* 2.8 1.49 0.73
  0.27 median(surgeon)* 6.1 2.38 0.73
  0.27 max(surgeon)* 29.9 8.80 0.73
  0.27 median adj.(surgeon)‡ 35.3 10.25 0.73
  1. ICC: Intracluster correlation coefficient.
  2. † ICC was based upon median of observed values.
  3. * Average cluster size based upon actual cluster sizes across trials in the database.
  4. ‡ Average cluster size calculated using the formula (∑ni 2)/∑ni) where ni is the number of observations in the ith cluster.
  5. χ Design effect was calculated using 1+(average cluster size-1)*ρ and 1-ρ for expertise-based trial and stratified design respectively.