Decision making within the context of drug development is continually becoming more and more complex. We strive to move forward the compounds with the strongest benefit risk profile, utilizing the right dose, and in the right patient population, in order to best address the unmet needs of patients. Bayesian methods, modeling, and simulation, are vitally important to improve the quality of decisions throughout this complex drug development process. At Lilly, there is now more routine use of quantitative information produced via the use of Bayesian methods, modeling, and simulation, which has improved the quality of decisions. Decision-makers are able to augment their own personal experience with the quantitative information provided by statisticians. In this talk, we discuss key principles that must be considered by the statistician when producing quantitative information to provide to decision-makers, as well as highlight examples of the types of decisions impacted via the modeling and simulation exercise.