Accepted Solutions
Hi @PolygonBison420,
Welcome in the Community !
In order to create a similar design, you can go in "DoE" menu, then "Classical" and "Response Surface Design".
You can then specify the 3 continuous factor and 3 responses.
Then you have the choice between different designs :
The CCD with Uniform Precision does contain 6 centre points, like in your example.
Then, select the axial value corresponding to rotatable design (1,682 for 3 continuous factors) :
And you'll end up with a similar design to the one you have shown. Here is the script to generate the design :
DOE(
Response Surface Design,
{Add Response( Maximize, "Capacity factor (k)", ., ., . ),
Add Response( Minimize, "Retention time (Rt2)", ., ., . ),
Add Response( Maximize, "Resolution (RS12)", ., ., . ),
Change Factor Settings( 1, 55, 65, "A: Organic Solvent" ),
Change Factor Settings( 2, 0.8, 1.2, "B: Flow rate" ),
Add Factor( Continuous, 3, 4, "C: pH", 0 ), Set Random Seed( 31406552 ),
Make Design( 2 ), Set Axial Choice( 1 ), Center Points( 6 ),
Simulate Responses( 0 ), Save X Matrix( 0 ), Set Run Order( Randomize ),
Make Table}
)For more infos about Response Surface Designs, you can look here : Build a Response Surface Design (jmp.com)
In order to analyze each model linked to the responses, you can have a look here : Standard Least Squares Models (jmp.com)
I attach the design datatable with a script "Fit Least Squares" that provides the analysis of the responses (please take note that I am not sure that the target for each response is correct, i.e Capacity factor should be maximized, Retention time should be minimized, and Resolution should be maximized ?).
You can try it yourself by launching the script "Model", selecting the responses (model is already defined, but if you have to do it manually you can select the factors and use the macro "Response Surface") and check "Fit Separately". You can then compare the models in the publication with yours.
Hope this answer will help you,
Hi @PolygonBison420,
Welcome in the Community !
In order to create a similar design, you can go in "DoE" menu, then "Classical" and "Response Surface Design".
You can then specify the 3 continuous factor and 3 responses.
Then you have the choice between different designs :
The CCD with Uniform Precision does contain 6 centre points, like in your example.
Then, select the axial value corresponding to rotatable design (1,682 for 3 continuous factors) :
And you'll end up with a similar design to the one you have shown. Here is the script to generate the design :
DOE(
Response Surface Design,
{Add Response( Maximize, "Capacity factor (k)", ., ., . ),
Add Response( Minimize, "Retention time (Rt2)", ., ., . ),
Add Response( Maximize, "Resolution (RS12)", ., ., . ),
Change Factor Settings( 1, 55, 65, "A: Organic Solvent" ),
Change Factor Settings( 2, 0.8, 1.2, "B: Flow rate" ),
Add Factor( Continuous, 3, 4, "C: pH", 0 ), Set Random Seed( 31406552 ),
Make Design( 2 ), Set Axial Choice( 1 ), Center Points( 6 ),
Simulate Responses( 0 ), Save X Matrix( 0 ), Set Run Order( Randomize ),
Make Table}
)For more infos about Response Surface Designs, you can look here : Build a Response Surface Design (jmp.com)
In order to analyze each model linked to the responses, you can have a look here : Standard Least Squares Models (jmp.com)
I attach the design datatable with a script "Fit Least Squares" that provides the analysis of the responses (please take note that I am not sure that the target for each response is correct, i.e Capacity factor should be maximized, Retention time should be minimized, and Resolution should be maximized ?).
You can try it yourself by launching the script "Model", selecting the responses (model is already defined, but if you have to do it manually you can select the factors and use the macro "Response Surface") and check "Fit Separately". You can then compare the models in the publication with yours.
Hope this answer will help you,
Thanks a lot for the link.
I'm checking the analysis results from the script "Fit Least Squares" I added in the datatable, you'll have very similar results (if not identical) to what is described and analyzed in the publication.
Concerning the optimization goals (maximize/minimize), it seems my initial guess was right, as when I am trying to optimize all responses with the Prediction Profiler from the "Fit Group", I have an optimum at 56,09 for factor A, 0,8 for factor B (flow rate) and 4 for factor C (pH) :
Compared to 56,1 for A, 0,8 for B and 3,7 for C in the publication :
However, I am surprised by the results of the predictions of the validation point from the publication, as Retention Time and Resolution have different prediction results when predicting in JMP, compared to the values in the publication, despite having similar models and similar prediction equations.
Here are my predicted values for the optimum found in the publication and with the same terms in the responses models :
I don't understand how predicted values can be so different (and not in the confidence intervals) between the publication and JMP (more noticeable for Resolution and Retention Time) ? I also tried relaunching a model with 3-factors interaction and cubic power terms (even if in the publication they mentioned only quadratic model), but that didn't create predicted values closer to what is obtained in terms of measured values and predicted values in the paper.
As the content related to analysis is quite light, I don't know exactly how they are obtaining these predicted values for the optimum.
If anyone has an idea, feel free to solve this mystery
