- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Report Inappropriate Content
Information tools for analysis of Definitive Screening Designs
Hello,
In the JMP course on Statistical Thinking for Industrial Problem Solving, the module on DOE does not handle the specific analysis of Definitive Screening Designs (DSD). Any other source of information that can be helpful for someone who is more familiar to the analysis of factorial designs but new to DSD analysis?
Thank you
Sara
Accepted Solutions
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Report Inappropriate Content
Re: Information tools for analysis of Definitive Screening Designs
Hi @SaraA,
When using the "Fit Definitive Screening", the analysis of Definitive Screening Designs is done in 2 steps to take into account the specific structure of DSD:
- First stage involves main effects identification with the responses values,
- Second stage involves 2-factors interactions and quadratic effects identification (based on Effects Heredity principle) with the responses residuals from the first stage model.
To learn more about the analysis method of DSDs available in the "Fit Definitive Screening Design", I can recommend some ressources and presentations :
- JMP Help section The Fit Definitive Screening Platform and more particularly Statistical Details for the Fit Definitive Screening Platform to have more precision and details about the method
- The original paper describing the analysis : Bradley Jones & Christopher J. Nachtsheim (2016): Effective Design-Based Model Selection for Definitive Screening Designs, Technometrics, DOI: 10.1080/00401706.2016.1234979
- Presentation by Bradley Jones about the Use of "Fit Definitive Screening" for other designs (foldover) and explanation of the method : A Surprising Use of the Fit Definitive Screening Platform (2022-EU-45MP-1066) - JMP User Community
- Mastering Using Definitive Screening Designs to Get More Information from Fewer Trials - JMP User Community by Tom Donelly
- Previous response to this question : Solved: Re: Significance of factors in Definitive Screening Design - JMP User Community
I hope these ressources will help you understand the logic behind this analysis method and model fitting.
"It is not unusual for a well-designed experiment to analyze itself" (Box, Hunter and Hunter)
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Get Direct Link
- Report Inappropriate Content
Re: Information tools for analysis of Definitive Screening Designs
Hi @SaraA,
When using the "Fit Definitive Screening", the analysis of Definitive Screening Designs is done in 2 steps to take into account the specific structure of DSD:
- First stage involves main effects identification with the responses values,
- Second stage involves 2-factors interactions and quadratic effects identification (based on Effects Heredity principle) with the responses residuals from the first stage model.
To learn more about the analysis method of DSDs available in the "Fit Definitive Screening Design", I can recommend some ressources and presentations :
- JMP Help section The Fit Definitive Screening Platform and more particularly Statistical Details for the Fit Definitive Screening Platform to have more precision and details about the method
- The original paper describing the analysis : Bradley Jones & Christopher J. Nachtsheim (2016): Effective Design-Based Model Selection for Definitive Screening Designs, Technometrics, DOI: 10.1080/00401706.2016.1234979
- Presentation by Bradley Jones about the Use of "Fit Definitive Screening" for other designs (foldover) and explanation of the method : A Surprising Use of the Fit Definitive Screening Platform (2022-EU-45MP-1066) - JMP User Community
- Mastering Using Definitive Screening Designs to Get More Information from Fewer Trials - JMP User Community by Tom Donelly
- Previous response to this question : Solved: Re: Significance of factors in Definitive Screening Design - JMP User Community
I hope these ressources will help you understand the logic behind this analysis method and model fitting.
"It is not unusual for a well-designed experiment to analyze itself" (Box, Hunter and Hunter)