“…However, as shown in Figure 2 and Figure 3 , even if it is generated within the two SDs, when the number of subjects is small, it is highly likely that the parameter estimate is different from the value used for simulation. The accuracy and precision of the population PK/PD parameter estimates are affected by various factors, including the sample size of patients, the number of measurements per patient, sparse or intensive sampling design, the degree of the BSV, and the magnitude of the within-subject variability (WSV) [ 5 , 26 ]. For a one-compartment model with first-order absorption, the sample size required to estimate the absorption rate within a precision level of 20% for a 95% confidence interval and a power of 90% was 30 for a sparse three-sampling scheme and 20 for a dense six-sampling scheme [ 27 ].…”