In this presentation, we explore the practical application of JMP Profiler, focusing on its improved feature of incorporating prediction intervals. Through a detailed case study from Cencora-PharmaLex, we demonstrate how prediction intervals provide a more robust framework for decision making by quantifying the uncertainty in model predictions. This added feature allows for more informed decisions, particularly in critical scenarios where risk management and precise predictions are essential. Through this case study, we will highlight the added value of prediction intervals in improving the reliability of data-driven decisions, ultimately leading to better outcomes in pharmaceutical and life sciences projects.

We also review the current capacity of JMP’s simulator, which does not yet incorporate predictive distributions to support risk-based decisions in the same manner. By addressing this limitation with examples and formulas, we aim to highlight opportunities for further enhancements in future JMP releases, ultimately leading to better outcomes in pharmaceutical and life sciences projects.