Skip to main content

Archived Comments for: Early intervention for adolescents with Patellofemoral Pain Syndrome - a pragmatic cluster randomised controlled trial

Back to article

  1. Wrong power calculation and analysis

    David J Torgerson, York University

    1 March 2012

    You are doing a cluster randomised controlled trial. However, your sample size is incorrect: you have not adjusted for clustering. Also your analysis strategy is incorrect: again you need to adjust for clustering. Even if you did the adjustment you only have 4 clusters, which is insufficient cluster replication. You need to increase the number of clusters to at least 8 and recalculate your sample size.

    Competing interests