Fig. 3From: 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?Plots of the mean trajectory in each treatment group of the trial for scenarios with residual error variance \({\sigma }_{e}^{2}=0.15\) (upper dashed line in each plot is for the control group and lower solid line for the treated group); treatment effects that are proportional to time are shown on the left and treatment effects that are not proportional to time on the rightBack to article page