Using Design of Experiments To Increase Predictability, Optimise Processes and Minimise Costs
Featuring: Damien Perret and Malcolm Moore
Design of experiments, or DOE, is a data-driven strategy that helps practitioners to better understand the underlying behaviour of a system by identifying those factors that most affect desired outcomes. By optimizing your experimental design, you can more effectively take prior information into account when setting up an experiment.
In this video, DOE experts Damien Perret, a research and development scientist at the French Atomic Energy Commission (CEA), and Malcolm Moore will show how you can accelerate learning cycles with a general, flexible method for experimentation.
Together, they will demonstrate how to use optimal designs which reduce the cost of experimentation, accommodate multiple types of factors and can be used even when the design space is constraine Optimal DOE is available in JMP® and is appropriate in virtually any situation that suggests the possible use of DOE.
You will learn how to:
- Drive optimal decisions by reducing the number of experimentation cycles, the elapsed time and the cost of data collection.
- Ensure you find the best solution to your problem using the Custom Design platform in JMP.
- Use JMP software’s Split Plot capabilities to produce good designs when the experiment imposes restrictions on the experimental run order.
- Mine existing data for correlated predictors, empty cells and outliers to better inform your next DOE.