When patient’s AUC and Cmax can be impacted not only by dosage but also by other factors (e.g., baseline level of creatinine clearance, age, gender, race), there will be greater need to individualize the dose for each subject instead of administering the same dose to everyone (one-dose-fits-all), so that the desired exposure can be achieved in more subjects. In this work we use bivariate linear regression to model the AUC and Cmax data and choose the dose level that maximizes the joint probability of the desired region for AUC and Cmax based on the model. Following this approach, individualized dosing rules are generated for new patients after modeling historical data such as that from early, ascending dose studies in humans. The performance of the proposed method is compared with the one-dose-fits-all approach using simulated data. Results from one simulation showed that 19% more patients would have AUC and Cmax in the desired region and therefore benefit from this approach. The macros for this methodology are created for easy implementation on real-world studies.