Skip to main content

Table 3 Outcome of power analysis for three outcomes for each study at each site (assuming six wards per site), and for both sites combined

From: Study protocol for two randomized controlled trials examining the effectiveness and safety of current weekend allied health services and a new stakeholder-driven model for acute medical/surgical patients versus no weekend allied health services

Outcome Proportion 1 (weekend allied health services)a Proportion 2 (no weekend allied health services) Single site or both sites combined Assumed coefficient of variation Assumed number of patients per study Power
Proportion of patients who stay longer than their AR-DRG average inlier length of stay 0.40 0.42 Single 0.4 n = 7,000b 0.65
Proportion of patients who are readmitted within 28 days 0.10 0.12 Single 0.4 n = 7,000b 0.96
Proportion of patients who experience at least one of the adverse events listed 0.10 0.12 Single 0.4 n = 7,000b 0.96
Proportion of patients who stay longer than their AR-DRG average inlier length of stay 0.40 0.42 Both 0.4 n = 14,000b 0.99
Proportion of patients who are readmitted within 28 days 0.10 0.12 Both 0.4 n = 14,000b >0.99
Proportion of patients who experience at least one of the adverse events listed 0.10 0.12 Both 0.4 n = 14,000b >0.99
  1. AR-DRG, Australian Refined Diagnosis-Related Group.
  2. aBaseline proportions based on data drawn from administrative datasets at participating sites covering a 12-month period.
  3. bNote that for the single site analyses we assume there will be 7,308 per study, but use only 7,000 in the power analysis to allow for loss of patients during the transition phases between intervention and control conditions and for transfers between study wards. Correspondingly, we use 14,000 when considering the power of both sites combined.