Fig. 8From: How important is the linearity assumption in a sample size calculation for a randomised controlled trial where treatment is anticipated to affect a rate of change?5-year trials with non-proportional treatment effects and smaller residual error variance. Left-hand panel: mean treatment effect at 5Â years, converted from differences in slopes between the treatment groups for the random slopes and linear trajectories, free covariances models. Right-hand panel: power. Ranges are \(\pm 1.96\) times the Monte Carlo standard errorBack to article page