Fig. 5

PuMBA and SiMBA were applied to the same simulated datasets in each condition, with identical priors on all shared parameters to compare their performance. Note that the measurement error sigma is equal to approximately double the original measurement error [23]. Black lines refer to the performance of these models applied to the true values underlying the simulations: univariate LME applied to the binding parameter, and multivariate PuMBA analysis applied to the true values of all the pharmacokinetic parameters. A MCMC sampling times for PuMBA and SiMBA per iteration. B Power as a function of sample size for a 0.182 (20%) difference between patients and controls. The shaded area represents the upper and lower bounds of the 95% confidence interval obtained using bootstrap resampling. C Standard error of group difference estimates as a function of sample size. D Mean estimated group differences across simulated datasets, with the true difference of 0.182 shown with a dashed black line. The shaded area represents the standard deviation of estimated group differences across simulations for each approach, with their individual boundaries emphasised with dotted lines