Fig. 4

TACs were simulated with the standard deviation of measurement error equal to the same, half, double or quadruple the estimated measurement error in the original data, represented with colours and modelled with LME or with PuMBA. A Power as a function of sample size for a 0.1 difference between patients and controls. The black dashed line represents the power of the LME analysis applied to the true values of \(BP_{\text {P}}\) from which the simulations were generated. B Mean standard error of the estimated group differences across the simulated datasets. The black dashed line represents the mean standard error of the LME analysis applied to the true values of \(BP_{\text {P}}\). C Mean estimated group differences across simulated datasets, with the true difference of 0.1 shown with a dashed black line. The error bars represent the standard deviation of estimated group differences across simulations, shown only for the original measurement error