Did It Have an Impact or Not? Using JMP® for the Design and Analysis of an Experiment in a Vaccine Product Root Cause Investigation
Janet Alvarado, Merck & Co.
During the investigation of an observed downward trend in the potency of a vaccine bulk material, a list of recent changes to process and/or methods showed that several had been implemented around the same timeframe. Analysis of historical data in this case does not provide conclusive information for deciding which one of these changes is the largest contributor to the issue or by how much. Use of Design of Experiments (DOE) is a better approach at quantifying the impact of a given change or set of changes. When there are hard-to-change factors, a split-plot design structure needs to be considered and appropriately analyzed to correctly assess statistical significance of the different factors. JMP statistical software is one of the few off-the-shelf packages that makes analysis of split-plot designs accessible to the industrial practitioner.