Hello everyone,
I hope you’re doing well.
I’m a master’s student currently working on a research project involving a Definitive Screening Design (DSD) in JMP for optimizing a Vertical Axis Wind Turbine (VAWT). I completed all 22 runs in my DSD (8 factors including 1 categorial factor), but I am struggling with the analysis phase.
Right now, my main issues are:
-
Only two main factors appear significant
-
The model R² is around 0.6, which makes me unsure whether the model is reliable
-
I’m unsure how to proceed with variable selection or next steps after a DSD
My ultimate goal is to transition from the DSD into a Response Surface Model (RSM) for optimization. I know that JMP can generate an RSM directly from a DSD when the number of active factors is below four, but I am not sure how to properly choose those factors or how to perform this step correctly. I also read that model selection can be based on AIC, BIC, or other criteria instead of just p-values, but I’m unsure how to apply this correctly in the context of a DSD.
At this point I am honestly a bit lost, and I am running out of time as the deadline is very near. It feels like I am doing something wrong, and I want to make sure I interpret the design correctly before moving forward.
If anyone experienced with DSD analysis in JMP is willing to take a quick 15–20 minute call to guide me or point me in the right direction, I would be extremely grateful. I am more than happy to mention your name in the acknowledgments section of my thesis/paper as appreciation for your help.
Thank you very much in advance to anyone who can assist. Any advice, clarification, or recommended steps would mean a lot.
Best regards,
