Reliability and efficiency of the D, E, S, A-optimal sampling schedule design

Due to the sharp practical and ethical constraints imposed on medical measurements, the parameter estimation procedure that is designed for diagnosis and therapy is often a difficult problem. When blood sampling provides the data, the number of samples and the measurement interval should be minimised. We have implemented D (determinant), E (eigenvalue), S (sensitivity) and A (trace) optimal sampling schedules (OSSs). These OSSs have minimal size, which means that the number of samples is equal to the number of model parameters that are being estimated. Setting up the results of the D, E, S and A approaches allows us to compare their efficiency and usefulness. Illustrative examples are presented.