Fig. 6
Observations versus Predictions. This figure shows observed data versus the corresponding ODE model predictions computed using the individual parameters. The 90% prediction interval, which depends on the residual error model, is overlaid. The residual error model shown above is the combined 1 error model. Predictions that are outside of the interval are denoted as outliers. A high proportion of outliers suggest misspecifications in the structural model, which we do not see here. Note also that the distribution of the observations is fairly symmetrical around the corresponding predicted values, as it should be.
